You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/06/10 06:47:58 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@6fca5c657a2fadc16fd7ff44de8a6a9656d50c1b)
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 56b46b38b deploying docs (apache/tvm@6fca5c657a2fadc16fd7ff44de8a6a9656d50c1b)
56b46b38b is described below
commit 56b46b38b2f6ea22f7557b9cac3b61d2cf87da50
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Jun 10 06:47:53 2022 +0000
deploying docs (apache/tvm@6fca5c657a2fadc16fd7ff44de8a6a9656d50c1b)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 2031 +++++++++++---------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 86 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 12 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 16 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 136 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 24 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 90 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2031 +++++++++++---------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 86 +-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 12 +-
.../work_with_microtvm/sg_execution_times.html | 14 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/doxygen/classes.html | 28 +-
...__schedule_1_1PySearchStrategyNode-members.html | 4 +-
..._1_1meta__schedule_1_1PySearchStrategyNode.html | 37 +-
...hedule_1_1PySearchStrategyNode__coll__graph.svg | 144 +-
...asstvm_1_1meta__schedule_1_1SearchStrategy.html | 4 +-
...ta__schedule_1_1SearchStrategyNode-members.html | 2 +-
...vm_1_1meta__schedule_1_1SearchStrategyNode.html | 19 +-
...1meta__schedule_1_1TuneContextNode-members.html | 103 +-
...sstvm_1_1meta__schedule_1_1TuneContextNode.html | 130 +-
...a__schedule_1_1TuneContextNode__coll__graph.svg | 669 +++----
...schedule_1_1TuneContextNode__inherit__graph.svg | 137 +-
.../api/doxygen/feature__extractor_8h_source.html | 2 +-
docs/reference/api/doxygen/functions__.html | 15 +
docs/reference/api/doxygen/functions_f.html | 2 +-
docs/reference/api/doxygen/functions_func.html | 15 +
docs/reference/api/doxygen/functions_func_n.html | 4 +-
docs/reference/api/doxygen/functions_func_t.html | 4 +-
docs/reference/api/doxygen/functions_m.html | 2 +-
docs/reference/api/doxygen/functions_n.html | 4 +-
docs/reference/api/doxygen/functions_s.html | 6 +-
docs/reference/api/doxygen/functions_t.html | 4 +-
docs/reference/api/doxygen/functions_type.html | 2 +-
docs/reference/api/doxygen/hierarchy.html | 75 +-
docs/reference/api/doxygen/inherit_graph_10.svg | 16 +-
docs/reference/api/doxygen/inherit_graph_107.svg | 32 +-
docs/reference/api/doxygen/inherit_graph_162.svg | 21 +-
docs/reference/api/doxygen/inherit_graph_163.svg | 24 +-
docs/reference/api/doxygen/inherit_graph_164.svg | 21 +-
docs/reference/api/doxygen/inherit_graph_165.svg | 18 +-
docs/reference/api/doxygen/inherit_graph_166.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_167.svg | 18 +-
docs/reference/api/doxygen/inherit_graph_168.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_169.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_170.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_171.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_172.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_173.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_174.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_175.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_176.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_177.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_178.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_179.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_180.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_181.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_182.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_183.svg | 14 +-
docs/reference/api/doxygen/inherit_graph_184.svg | 14 +-
docs/reference/api/doxygen/inherit_graph_185.svg | 28 +-
docs/reference/api/doxygen/inherit_graph_186.svg | 29 +-
docs/reference/api/doxygen/inherit_graph_187.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_188.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_189.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_190.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_191.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_192.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_193.svg | 17 +-
docs/reference/api/doxygen/inherit_graph_194.svg | 17 +-
docs/reference/api/doxygen/inherit_graph_195.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_196.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_197.svg | 14 +-
docs/reference/api/doxygen/inherit_graph_198.svg | 17 +-
docs/reference/api/doxygen/inherit_graph_199.svg | 80 +-
docs/reference/api/doxygen/inherit_graph_200.svg | 70 +-
docs/reference/api/doxygen/inherit_graph_201.svg | 79 +-
docs/reference/api/doxygen/inherit_graph_202.svg | 19 +-
docs/reference/api/doxygen/inherit_graph_203.svg | 19 +-
docs/reference/api/doxygen/inherit_graph_204.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_205.svg | 15 +-
docs/reference/api/doxygen/inherit_graph_206.svg | 29 +-
docs/reference/api/doxygen/inherit_graph_207.svg | 24 +-
docs/reference/api/doxygen/inherit_graph_208.svg | 30 +-
docs/reference/api/doxygen/inherit_graph_209.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_210.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_211.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_212.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_213.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_214.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_215.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_216.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_217.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_218.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_219.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_220.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_221.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_222.svg | 12 +-
docs/reference/api/doxygen/inherit_graph_223.svg | 12 +-
...inherit_graph_223.svg => inherit_graph_224.svg} | 0
docs/reference/api/doxygen/inherit_graph_39.svg | 16 +-
docs/reference/api/doxygen/inherit_graph_42.svg | 8 +-
docs/reference/api/doxygen/inherit_graph_43.svg | 8 +-
docs/reference/api/doxygen/inherits.html | 126 +-
.../meta__schedule_2cost__model_8h_source.html | 2 +-
docs/reference/api/doxygen/mutator_8h_source.html | 2 +-
docs/reference/api/doxygen/postproc_8h_source.html | 2 +-
.../api/doxygen/schedule__rule_8h_source.html | 2 +-
docs/reference/api/doxygen/search/all_1.js | 5 +
docs/reference/api/doxygen/search/all_10.js | 2 +-
docs/reference/api/doxygen/search/all_13.js | 2 +-
docs/reference/api/doxygen/search/all_14.js | 14 +-
docs/reference/api/doxygen/search/all_15.js | 11 +-
docs/reference/api/doxygen/search/all_16.js | 2 +-
docs/reference/api/doxygen/search/all_17.js | 4 +-
docs/reference/api/doxygen/search/all_18.js | 2 +-
docs/reference/api/doxygen/search/all_7.js | 2 +-
docs/reference/api/doxygen/search/all_e.js | 4 +-
docs/reference/api/doxygen/search/all_f.js | 2 +-
docs/reference/api/doxygen/search/classes_10.js | 8 +-
docs/reference/api/doxygen/search/classes_11.js | 3 +-
docs/reference/api/doxygen/search/classes_13.js | 4 +-
docs/reference/api/doxygen/search/functions_0.js | 7 +-
docs/reference/api/doxygen/search/functions_12.js | 2 +-
docs/reference/api/doxygen/search/functions_13.js | 2 +-
docs/reference/api/doxygen/search/functions_14.js | 4 +-
docs/reference/api/doxygen/search/functions_15.js | 2 +-
docs/reference/api/doxygen/search/functions_d.js | 2 +-
docs/reference/api/doxygen/search/functions_e.js | 2 +-
docs/reference/api/doxygen/search/functions_f.js | 2 +-
docs/reference/api/doxygen/search/typedefs_5.js | 2 +-
.../api/doxygen/search__strategy_8h_source.html | 24 +-
.../api/doxygen/space__generator_8h_source.html | 2 +-
.../api/doxygen/tune__context_8h_source.html | 45 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 6 +-
docs/tutorial/autotvm_relay_x86.html | 258 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
239 files changed, 4810 insertions(+), 4136 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index ecc1e061b..55f149087 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb9a21007-85fe-4ff4-bf19-98da9769e6be from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip5772ac00-f1cd-4fd2-87d6-a521d7e88b81 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index b5947a24d..e3a0c47b3 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -100,7 +100,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:11, 88.5kB/s]
0%| | 48.0k/41.5M [00:00<05:09, 140kB/s]
0%| | 104k/41.5M [00:00<03:20, 217kB/s]
0%| | 208k/41.5M [00:00<02:01, 358kB/s]
1%| | 424k/41.5M [00:00<01:05, 658kB/s]
2%|2 | 864k/41.5M [00:01<00:33, 1.26MB/s]
4%|4 | 1.70M/41.5M [00:01<00:17, 2.42MB/s]
7%|6 | 2.88M/41.5M [00:01<00:10, 3.78MB/s]
10%|9 | 4.12M/41.5M [00:01<00:08, 4.77MB/s]
13%|#3 | 5.41M/41.5M [00:01<00:06, 5.56MB/s]
16%|#6 | 6.78M/41.5M [00:02<00:05, 6.22MB/s]
20%|#9 | 8.20M/41.5M [00:02<00:05, 6.76MB/s]
23%|##3 | 9.67M/41.5M [00:02<00:04, 7.23MB/s]
27%|##6 | 11.1M/41.5M [00:02<00:04, 7.56MB/s]
30%|### | 12.6M/41.5M [00:02<00:03, 7.76MB/s]
34%|###3 | 14.1M/41.5M [00:02<00:03, 7.92MB/s]
37%|###7 | 15.6M/41.5M [00:03<00
:03, 8.02MB/s]
41%|####1 | 17.0M/41.5M [00:03<00:03, 8.10MB/s]
45%|####4 | 18.5M/41.5M [00:03<00:02, 8.16MB/s]
48%|####8 | 20.0M/41.5M [00:03<00:02, 8.20MB/s]
52%|#####1 | 21.4M/41.5M [00:03<00:02, 8.22MB/s]
55%|#####5 | 22.9M/41.5M [00:04<00:02, 8.24MB/s]
59%|#####8 | 24.4M/41.5M [00:04<00:02, 8.26MB/s]
62%|######2 | 25.9M/41.5M [00:04<00:01, 8.27MB/s]
66%|######5 | 27.3M/41.5M [00:04<00:01, 8.28MB/s]
69%|######9 | 28.8M/41.5M [00:04<00:01, 8.55MB/s]
73%|#######2 | 30.2M/41.5M [00:04<00:01, 9.78MB/s]
75%|#######5 | 31.2M/41.5M [00:05<00:01, 9.52MB/s]
78%|#######7 | 32.2M/41.5M [00:05<00:01, 8.11MB/s]
80%|######## | 33.2M/41.5M [00:05<00:01, 8.43MB/s]
84%|########3 | 34.7M/41.5M [00:05<00:00, 8.37MB/s]
87%|########7 | 36.1M/41.5M [00:05<00:00, 9.76MB/s]
89%|########9 | 37.1M/41.5M [00:05<00:00, 8.71MB/s]
92%|#########1| 38.0M/41.5M [00:05<00:00, 7.49MB/s]
94%|####
#####4| 39.1M/41.5M [00:06<00:00, 8.06MB/s]
98%|#########7| 40.5M/41.5M [00:06<00:00, 9.60MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 6.86MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:31, 96.3kB/s]
0%| | 48.0k/41.5M [00:00<04:49, 150kB/s]
0%| | 88.0k/41.5M [00:00<03:52, 186kB/s]
0%| | 128k/41.5M [00:00<03:35, 201kB/s]
0%| | 184k/41.5M [00:00<03:00, 240kB/s]
1%| | 232k/41.5M [00:01<02:55, 247kB/s]
1%| | 288k/41.5M [00:01<02:42, 266kB/s]
1%| | 344k/41.5M [00:01<02:35, 278kB/s]
1%| | 408k/41.5M [00:01<02:22, 301kB/s]
1%|1 | 472k/41.5M [00:01<02:16, 316kB/s]
1%|1 | 536k/41.5M [00:02<02:11, 326kB/s]
1%|1 | 608k/41.5M [00:02<02:04, 345kB/s]
2%|1 | 688k/41.5M [00:02<01:55, 370kB/s]
2%|1 | 760k/41.5M [00:02<01:54, 373kB/s]
2%|1 | 840k/41.5M [00:02<01:49, 389kB/s]
2%|2 | 928k/41.5M [00:02<01:42, 414kB/s]
2%|2 | 0.99M/41.5M [00:03<01:37, 435kB/s]
3%|2 | 1.09M/41.5M [00:03<01:31, 465kB/s]
3%|2 | 1.19M/41.5M [00:03<01:24, 498kB/s]
3%|3 | 1.29M/41.5M [00:03<01:20, 521kB/s]
3%|3 | 1.39M/41.5M [00:03<01:18, 537kB/s]
4%|3 | 1.50M/41.5M [00:04<01:14, 559kB/s]
4%|3 | 1.61M/41.5M [00:04<01:12, 576kB/s]
4%|4 | 1.73M/41.5M [00:04<01:08, 605kB/s]
4%|4 | 1.85M/41.5M [00:04<01:04, 640kB/s]
5%|4 | 1.98M/41.5M [00:04<01:01, 678kB/s]
5%|5 | 2.12M/41.5M [00:05<00:58, 705kB/s]
5%|5 | 2.26M/41.5M [00:05<00:55, 735kB/s]
6%|5 | 2.41M/41.5M [00:05<00:50, 818kB/s]
6%|6 | 2.56M/41.5M [00:05<00:48, 845kB/s]
7%|6 | 2.73M/41.5M [00:05<00:46, 875kB/s]
7%|6 | 2.90M/41.5M [00:05<00:43, 932kB/s]
7%|7 | 3.09M/41.5M [00:06<00:45, 891kB/s]
8%|7 | 3.27M/41.5M [00:06<00:40, 995kB/s]
8%|8 | 3.48M/41.5M [00:06<00:38, 1.04
MB/s]
9%|8 | 3.68M/41.5M [00:06<00:33, 1.18MB/s]
9%|9 | 3.88M/41.5M [00:06<00:31, 1.26MB/s]
10%|9 | 4.01M/41.5M [00:06<00:33, 1.17MB/s]
10%|9 | 4.12M/41.5M [00:07<00:39, 992kB/s]
10%|# | 4.34M/41.5M [00:07<00:33, 1.15MB/s]
11%|#1 | 4.59M/41.5M [00:07<00:31, 1.22MB/s]
12%|#1 | 4.84M/41.5M [00:07<00:27, 1.42MB/s]
12%|#2 | 5.09M/41.5M [00:07<00:24, 1.55MB/s]
13%|#2 | 5.25M/41.5M [00:07<00:26, 1.43MB/s]
13%|#2 | 5.39M/41.5M [00:07<00:29, 1.30MB/s]
14%|#3 | 5.68M/41.5M [00:08<00:23, 1.59MB/s]
14%|#4 | 5.86M/41.5M [00:08<00:22, 1.65MB/s]
15%|#4 | 6.02M/41.5M [00:08<00:27, 1.36MB/s]
15%|#5 | 6.32M/41.5M [00:08<00:23, 1.58MB/s]
16%|#6 | 6.66M/41.5M [00:08<00:19, 1.90MB/s]
17%|#6 | 6.85M/41.5M [00:08<00:18, 1.93MB/s]
17%|#6 | 7.05M/41.5M [00:08<00:22, 1.64MB/s]
18%|#7 | 7
.39M/41.5M [00:09<00:18, 1.89MB/s]
19%|#8 | 7.77M/41.5M [00:09<00:15, 2.25MB/s]
20%|#9 | 8.17M/41.5M [00:09<00:14, 2.48MB/s]
20%|## | 8.42M/41.5M [00:09<00:15, 2.30MB/s]
21%|## | 8.65M/41.5M [00:09<00:16, 2.11MB/s]
22%|##1 | 9.10M/41.5M [00:09<00:13, 2.59MB/s]
23%|##3 | 9.58M/41.5M [00:09<00:11, 2.91MB/s]
24%|##3 | 9.87M/41.5M [00:10<00:12, 2.70MB/s]
24%|##4 | 10.1M/41.5M [00:10<00:13, 2.48MB/s]
26%|##5 | 10.7M/41.5M [00:10<00:10, 3.10MB/s]
27%|##7 | 11.2M/41.5M [00:10<00:08, 3.63MB/s]
28%|##7 | 11.6M/41.5M [00:10<00:09, 3.26MB/s]
29%|##8 | 11.9M/41.5M [00:10<00:10, 2.84MB/s]
30%|### | 12.5M/41.5M [00:10<00:08, 3.39MB/s]
32%|###1 | 13.1M/41.5M [00:10<00:07, 3.85MB/s]
33%|###3 | 13.8M/41.5M [00:11<00:06, 4.23MB/s]
34%|###4 | 14.2M/41.5M [00:11<00:07, 3.88MB/s]
35%|###5 | 14.6M/41.5M [00:11<00:08, 3.2
5MB/s]
37%|###6 | 15.3M/41.5M [00:11<00:07, 3.87MB/s]
39%|###8 | 16.1M/41.5M [00:11<00:05, 4.82MB/s]
40%|###9 | 16.6M/41.5M [00:11<00:05, 4.42MB/s]
41%|####1 | 17.0M/41.5M [00:11<00:06, 3.75MB/s]
43%|####2 | 17.8M/41.5M [00:12<00:05, 4.45MB/s]
45%|####5 | 18.8M/41.5M [00:12<00:04, 5.62MB/s]
47%|####6 | 19.3M/41.5M [00:12<00:04, 5.15MB/s]
48%|####7 | 19.9M/41.5M [00:12<00:05, 4.41MB/s]
50%|##### | 20.8M/41.5M [00:12<00:04, 5.23MB/s]
53%|#####2 | 21.9M/41.5M [00:12<00:03, 6.58MB/s]
54%|#####4 | 22.5M/41.5M [00:12<00:03, 6.08MB/s]
56%|#####5 | 23.2M/41.5M [00:13<00:03, 5.24MB/s]
58%|#####8 | 24.2M/41.5M [00:13<00:02, 6.12MB/s]
61%|######1 | 25.4M/41.5M [00:13<00:02, 6.46MB/s]
64%|######4 | 26.8M/41.5M [00:13<00:01, 7.95MB/s]
66%|######6 | 27.6M/41.5M [00:13<00:01, 7.34MB/s]
68%|######8 | 28.3M/41.5M [00:13<00:02, 6.34MB/s]
71%|#######1 |
29.6M/41.5M [00:13<00:01, 7.37MB/s]
75%|#######4 | 31.0M/41.5M [00:14<00:01, 8.91MB/s]
77%|#######7 | 32.0M/41.5M [00:14<00:01, 8.41MB/s]
79%|#######9 | 32.8M/41.5M [00:14<00:01, 7.12MB/s]
82%|########1 | 34.0M/41.5M [00:14<00:00, 8.22MB/s]
85%|########5 | 35.4M/41.5M [00:14<00:00, 9.85MB/s]
88%|########7 | 36.4M/41.5M [00:14<00:00, 8.46MB/s]
90%|######### | 37.3M/41.5M [00:14<00:00, 7.30MB/s]
93%|#########2| 38.4M/41.5M [00:15<00:00, 8.05MB/s]
96%|#########5| 39.8M/41.5M [00:15<00:00, 9.69MB/s]
98%|#########8| 40.8M/41.5M [00:15<00:00, 8.33MB/s]
100%|##########| 41.5M/41.5M [00:15<00:00, 2.80MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 35adcc0a1..4746226df 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -210,7 +210,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.558 seconds)
+ **Total running time of the script:** ( 1 minutes 6.977 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index e2cb190af..33c96d832 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
36%|###5 | 15.9M/44.7M [00:00<00:00, 166MB/s]
84%|########4 | 37.7M/44.7M [00:00<00:00, 203MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 207MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
6%|5 | 2.62M/44.7M [00:00<00:01, 26.9MB/s]
12%|#1 | 5.20M/44.7M [00:00<00:02, 14.9MB/s]
17%|#7 | 7.69M/44.7M [00:00<00:02, 18.5MB/s]
22%|##1 | 9.75M/44.7M [00:00<00:02, 17.5MB/s]
26%|##5 | 11.6M/44.7M [00:00<00:02, 14.0MB/s]
31%|### | 13.8M/44.7M [00:00<00:02, 16.0MB/s]
35%|###4 | 15.5M/44.7M [00:01<00:02, 14.1MB/s]
38%|###8 | 17.1M/44.7M [00:01<00:01, 14.7MB/s]
42%|####1 | 18.6M/44.7M [00:01<00:01, 14.3MB/s]
46%|####6 | 20.7M/44.7M [00:01<00:01, 16.2MB/s]
52%|#####1 | 23.0M/44.7M [00:01<00:01, 18.3MB/s]
56%|#####5 | 24.9M/44.7M [00:01<00:01, 17.5MB/s]
60%|#####9 | 26.7M/44.7M [00:01<00:01, 18.0MB/s]
64%|######3 | 28.5M/44.7M [00:01<00:00, 17.8MB/s]
69%|######9 | 30.9M/44.7M [00:01<00:00, 19.8MB/s]
74%|#######4 | 33.1M/44.7M [00:02<00:00, 20.7MB/s]
80%|#######9 | 35.7M/44.7M [00
:02<00:00, 22.3MB/s]
85%|########4 | 37.8M/44.7M [00:02<00:00, 22.3MB/s]
90%|########9 | 40.2M/44.7M [00:02<00:00, 22.9MB/s]
95%|#########4| 42.4M/44.7M [00:02<00:00, 22.8MB/s]
100%|##########| 44.7M/44.7M [00:02<00:00, 18.7MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index 292fc8196..e469081e9 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -381,7 +381,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.332 seconds)
+ **Total running time of the script:** ( 1 minutes 2.780 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index d6696c57b..685c6dfd6 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,15 +5,15 @@
Computation times
=================
-**05:30.132** total execution time for **how_to_compile_models** files:
+**05:34.644** total execution time for **how_to_compile_models** files:
-- **01:09.558**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:04.332**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:58.774**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:32.201**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:24.105**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:23.026**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:21.769**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:19.896**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:13.875**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.596**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:06.977**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:02.780**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:57.892**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:40.873**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:24.682**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:22.335**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:21.765**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:21.084**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:13.744**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.511**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 0f7d87f5f..49e76dabd 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -402,7 +402,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0902 16.0877 16.2235 15.9769 0.0801
+ 15.6991 15.6979 15.7898 15.6255 0.0513
diff --git a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
index 1b600ab76..cd9f37407 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -108,7 +108,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 2.62M/170M [00:00<00:06, 27.1MB/s]
3%|3 | 5.21M/170M [00:00<00:06, 25.4MB/s]
6%|6 | 10.5M/170M [00:00<00:04, 38.2MB/s]
9%|8 | 14.4M/170M [00:00<00:04, 39.3MB/s]
11%|# | 18.2M/170M [00:00<00:04, 34.4MB/s]
13%|#2 | 21.9M/170M [00:00<00:04, 35.5MB/s]
15%|#5 | 25.7M/170M [00:00<00:04, 36.9MB/s]
19%|#8 | 31.4M/170M [00:00<00:03, 43.9MB/s]
22%|##1 | 36.7M/170M [00:00<00:02, 47.2MB/s]
24%|##4 | 41.2M/170M [00:01<00:02, 45.5MB/s]
27%|##6 | 45.6M/170M [00:01<00:03, 42.2MB/s]
29%|##9 | 49.7M/170M [00:01<00:03, 39.4MB/s]
32%|###1 | 53.6M/170M [00:01<00:03, 38.6MB/s]
34%|###4 | 58.2M/170M [00:01<00:02, 41.2MB/s]
37%|###6 | 62.2M/170M [00:01<00:03, 31.8MB/s]
39%|###8 | 66.1M/170M [00:01<00:03, 33.6MB/s]
41%|####1 | 69.8M/170M [00:01<00:03, 34.5MB/
s]
43%|####3 | 73.3M/170M [00:02<00:03, 32.9MB/s]
45%|####5 | 76.9M/170M [00:02<00:02, 34.0MB/s]
47%|####7 | 80.3M/170M [00:02<00:02, 33.2MB/s]
49%|####9 | 83.6M/170M [00:02<00:03, 27.8MB/s]
51%|##### | 86.4M/170M [00:02<00:03, 27.0MB/s]
52%|#####2 | 89.1M/170M [00:02<00:03, 26.8MB/s]
56%|#####5 | 95.0M/170M [00:02<00:02, 35.9MB/s]
58%|#####8 | 98.8M/170M [00:02<00:02, 36.9MB/s]
60%|###### | 102M/170M [00:03<00:02, 32.1MB/s]
62%|######2 | 106M/170M [00:03<00:02, 26.4MB/s]
65%|######4 | 110M/170M [00:03<00:02, 31.2MB/s]
67%|######6 | 114M/170M [00:03<00:02, 25.9MB/s]
69%|######8 | 116M/170M [00:03<00:02, 20.5MB/s]
70%|######9 | 119M/170M [00:03<00:02, 21.2MB/s]
71%|#######1 | 121M/170M [00:03<00:02, 22.3MB/s]
73%|#######2 | 124M/170M [00:04<00:02, 23.6MB/s]
75%|#######4 | 127M/170M [00:04<00:01, 25.2MB/s]
78%|#######7 | 132M/170M [00:04<00:01, 31.9M
B/s]
80%|######## | 137M/170M [00:04<00:00, 37.2MB/s]
83%|########2 | 140M/170M [00:04<00:01, 29.1MB/s]
85%|########4 | 144M/170M [00:04<00:01, 25.9MB/s]
86%|########6 | 146M/170M [00:04<00:00, 26.8MB/s]
88%|########7 | 149M/170M [00:04<00:00, 26.9MB/s]
90%|########9 | 152M/170M [00:05<00:00, 27.6MB/s]
92%|#########1| 156M/170M [00:05<00:00, 31.1MB/s]
94%|#########3| 159M/170M [00:05<00:00, 31.2MB/s]
96%|#########5| 163M/170M [00:05<00:00, 33.4MB/s]
98%|#########7| 166M/170M [00:05<00:00, 33.0MB/s]
100%|#########9| 169M/170M [00:05<00:00, 31.7MB/s]
100%|##########| 170M/170M [00:05<00:00, 31.7MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 4.06M/170M [00:00<00:04, 42.6MB/s]
5%|4 | 8.45M/170M [00:00<00:03, 44.5MB/s]
7%|7 | 12.7M/170M [00:00<00:03, 41.8MB/s]
10%|9 | 16.7M/170M [00:00<00:04, 38.4MB/s]
12%|#2 | 20.4M/170M [00:00<00:05, 28.8MB/s]
15%|#4 | 24.8M/170M [00:00<00:04, 33.2MB/s]
17%|#6 | 28.6M/170M [00:00<00:04, 34.7MB/s]
20%|#9 | 33.2M/170M [00:00<00:03, 38.7MB/s]
22%|##1 | 37.2M/170M [00:01<00:03, 37.1MB/s]
24%|##4 | 40.8M/170M [00:01<00:03, 37.4MB/s]
27%|##6 | 45.2M/170M [00:01<00:03, 39.6MB/s]
29%|##8 | 49.1M/170M [00:01<00:03, 39.0MB/s]
32%|###2 | 54.4M/170M [00:01<00:02, 43.5MB/s]
35%|###4 | 58.6M/170M [00:01<00:02, 43.8MB/s]
37%|###7 | 63.5M/170M [00:01<00:02, 45.7MB/s]
40%|#### | 68.1M/170M [00:01<00:02, 46.4MB/s]
43%|####2 | 72.6M/170M [00:01<00:02, 43.2MB/
s]
45%|####5 | 76.8M/170M [00:02<00:02, 42.0MB/s]
48%|####8 | 81.5M/170M [00:02<00:02, 44.2MB/s]
51%|##### | 85.8M/170M [00:02<00:02, 35.6MB/s]
53%|#####2 | 89.5M/170M [00:02<00:02, 34.4MB/s]
55%|#####4 | 93.0M/170M [00:02<00:02, 34.9MB/s]
57%|#####7 | 97.4M/170M [00:02<00:02, 37.7MB/s]
60%|###### | 102M/170M [00:02<00:01, 40.4MB/s]
63%|######2 | 107M/170M [00:02<00:01, 43.2MB/s]
65%|######5 | 111M/170M [00:03<00:01, 36.3MB/s]
68%|######7 | 115M/170M [00:03<00:01, 36.7MB/s]
70%|####### | 119M/170M [00:03<00:01, 39.5MB/s]
73%|#######3 | 124M/170M [00:03<00:01, 42.2MB/s]
76%|#######5 | 128M/170M [00:03<00:01, 40.4MB/s]
78%|#######7 | 132M/170M [00:03<00:01, 35.3MB/s]
80%|######## | 136M/170M [00:03<00:01, 33.9MB/s]
82%|########2 | 139M/170M [00:03<00:01, 29.5MB/s]
84%|########3 | 142M/170M [00:04<00:01, 26.7MB/s]
86%|########5 | 145M/170M [00:04<00:00, 27.9MB/
s]
88%|########8 | 150M/170M [00:04<00:00, 33.8MB/s]
91%|#########1| 155M/170M [00:04<00:00, 38.6MB/s]
94%|#########3| 159M/170M [00:04<00:00, 37.3MB/s]
96%|#########6| 164M/170M [00:04<00:00, 39.9MB/s]
99%|#########8| 168M/170M [00:04<00:00, 40.6MB/s]
100%|##########| 170M/170M [00:04<00:00, 37.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -262,7 +262,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 2.846 seconds)
+ **Total running time of the script:** ( 2 minutes 57.931 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_object_detection_pytorch.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
index 8155c6016..46261f236 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 182MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 201MB/s]
@@ -353,7 +353,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3933 90.3727 90.9154 90.2584 0.1033
+ 90.3258 90.2362 93.6856 90.0742 0.3973
@@ -393,7 +393,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.722 seconds)
+ **Total running time of the script:** ( 1 minutes 5.565 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
index f29354e73..346de0012 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -360,7 +360,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.0126 119.9351 125.6041 119.2173 0.6736
+ 118.4617 118.4777 119.7582 117.4165 0.3981
@@ -394,7 +394,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 58.798 seconds)
+ **Total running time of the script:** ( 1 minutes 58.398 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized_tflite.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
index a64db0bff..35d9f9190 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -223,7 +223,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 26.634 seconds)
+ **Total running time of the script:** ( 1 minutes 15.188 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_quantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
index f89a4cb2d..b0de4c572 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6237/132723 [00:00<00:02, 62363.52KB/s]
11%|#1 | 15067/132723 [00:00<00:01, 77614.76KB/s]
18%|#7 | 23815/132723 [00:00<00:01, 82114.21KB/s]
25%|##4 | 32633/132723 [00:00<00:01, 84507.19KB/s]
31%|###1 | 41418/132723 [00:00<00:01, 85709.94KB/s]
38%|###7 | 50270/132723 [00:00<00:00, 86663.93KB/s]
45%|####4 | 59145/132723 [00:00<00:00, 87341.75KB/s]
51%|#####1 | 67960/132723 [00:00<00:00, 87596.21KB/s]
58%|#####7 | 76843/132723 [00:00<00:00, 87979.09KB/s]
65%|######4 | 85641/132723 [00:01<00:00, 87802.14KB/s]
71%|#######1 | 94431/132723 [00:01<00:00, 87829.19KB/s]
78%|#######7 | 103229/132723 [00:01<00:00, 87869.57KB/s]
84%|########4 | 112058/132723 [00:01<00:00, 87993.88KB/s]
91%|#########1| 120858/132723 [00:01<00:00, 81135.56KB/s]
98%|#########7| 129784/132723 [00:01<00:00, 83440.76KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84857.48KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
2%|2 | 3237/132723 [00:00<00:04, 31959.25KB/s]
7%|6 | 9111/132723 [00:00<00:02, 47627.21KB/s]
13%|#3 | 17710/132723 [00:00<00:01, 65091.50KB/s]
20%|#9 | 26382/132723 [00:00<00:01, 73612.50KB/s]
26%|##6 | 35097/132723 [00:00<00:01, 78487.11KB/s]
33%|###3 | 43861/132723 [00:00<00:01, 81595.46KB/s]
39%|###9 | 52393/132723 [00:00<00:00, 82805.64KB/s]
46%|####6 | 61131/132723 [00:00<00:00, 84259.84KB/s]
53%|#####2 | 69817/132723 [00:00<00:00, 85065.63KB/s]
59%|#####9 | 78546/132723 [00:01<00:00, 85750.22KB/s]
66%|######5 | 87278/132723 [00:01<00:00, 86227.50KB/s]
72%|#######2 | 96002/132723 [00:01<00:00, 86534.30KB/s]
79%|#######8 | 104761/132723 [00:01<00:00, 86845.06KB/s]
85%|########5 | 113446/132723 [00:01<00:00, 85827.59KB/s]
92%|#########1| 122075/132723 [00:01<00:00, 85963.69KB/s]
99%|#########
8| 130841/132723 [00:01<00:00, 86467.68KB/s]
100%|##########| 132723/132723 [00:01<00:00, 81470.34KB/s]
@@ -211,7 +211,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 20.786 seconds)
+ **Total running time of the script:** ( 2 minutes 16.018 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_ssd_gluoncv.py:
diff --git a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
index 7dc7be50f..b9551b78f 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**10:49.110** total execution time for **how_to_deploy_models** files:
+**10:24.913** total execution time for **how_to_deploy_models** files:
-- **03:02.846**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:20.786**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:58.798**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:26.634**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:07.722**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:29.348**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.765**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.210**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **02:57.931**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:16.018**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:58.398**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:15.188**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:05.565**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:29.269**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:22.346**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.197**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 64c6156d6..4d34b7187 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -425,7 +425,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipd61adcdc-323e-4f61-bf3f-05c00fda9368 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip91778866-356d-48f0-83b8-4dc691e0c584 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 622134cb2..93e80769f 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,9 +5,9 @@
Computation times
=================
-**00:41.074** total execution time for **how_to_extend_tvm** files:
+**00:39.739** total execution time for **how_to_extend_tvm** files:
-- **00:37.248**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.465**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.145**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:36.044**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.410**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.086**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.199**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 79056a0ce..d35ac9228 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6867us [6867us] (45.97%; 45.97%)
- FoldScaleAxis: 8071us [7us] (54.03%; 54.03%)
- FoldConstant: 8064us [1594us] (53.98%; 99.91%)
- InferType: 6470us [6470us] (43.31%; 80.23%)
+ InferType: 7570us [7570us] (47.66%; 47.66%)
+ FoldScaleAxis: 8313us [7us] (52.34%; 52.34%)
+ FoldConstant: 8306us [1697us] (52.30%; 99.92%)
+ InferType: 6609us [6609us] (41.61%; 79.57%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6511us [6511us] (44.95%; 44.95%)
- FoldScaleAxis: 7974us [6us] (55.05%; 55.05%)
- FoldConstant: 7968us [1625us] (55.01%; 99.93%)
- InferType: 6343us [6343us] (43.79%; 79.60%)
+ InferType: 6582us [6582us] (44.59%; 44.59%)
+ FoldScaleAxis: 8179us [5us] (55.41%; 55.41%)
+ FoldConstant: 8174us [1666us] (55.38%; 99.94%)
+ InferType: 6509us [6509us] (44.09%; 79.62%)
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
index ca2d87f61..2c5b88ec2 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.152333 ms
+ Convolution: 54.144555 ms
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
index 481af432a..0a1384660 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 7.564221 ms
+ conv2d with tensor core: 8.206228 ms
diff --git a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
index ba29bf992..62d8f6f8b 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019254
- Baseline: 3.429668
+ Numpy running time: 0.018107
+ Baseline: 3.514277
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.305701
+ Opt1: 0.304224
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.336352
+ Opt2: 0.335820
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118276
+ Opt3: 0.120454
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110659
+ Opt4: 0.110737
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111297
+ Opt5: 0.111545
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145612
+ Opt6: 0.144740
diff --git a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
index d0a03bd31..15e4855cc 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:35.433** total execution time for **how_to_optimize_operators** files:
+**00:35.365** total execution time for **how_to_optimize_operators** files:
-- **00:32.652**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.494**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.287**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.708**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.429**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.228**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 853980169..9c9727d7f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**05:16.528** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:33.953**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:21.230**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:43.625**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:20.075**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.900**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.745**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:12.774** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:35.151**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:20.213**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:42.864**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:17.515**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.537**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.494**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 9d9414ff8..5f30e8e5d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -222,12 +222,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -235,470 +235,618 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
+ for (rc.outer.outer: int32, 0, 8) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_4: int32 = (rc.outer.outer*3136)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*576)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 49), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 98), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 147), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 147), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 147), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 196), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 245), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 245), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 245), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 294), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 294), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 294), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 343), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 343), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 343), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 392), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 335)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 490), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 490), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 490), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 539), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 539), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 539), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 588), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 637), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 637), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 637), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 686), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 686), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 686), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 735), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 735), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 735), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 833), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 833), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 678)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 931), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 931), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 931), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 980), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1029), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1029), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1029), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1078), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1078), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1078), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1127), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1127), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1127), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1225), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1225), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1225), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 1274), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1274), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1021)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1372), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1421), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1421), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1421), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1470), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1470), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1470), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1519), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1519), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1519), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1617), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1617), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1617), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1666), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1666), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1666), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 1715), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1715), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1813), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1813), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1813), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1862), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1862), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1862), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1911), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1911), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1911), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2009), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2009), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2009), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2058), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2058), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2058), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2107), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2107), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2107), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 2156), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2156), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1707)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2254), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2254), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2254), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2303), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2303), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2303), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2352), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2401), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2401), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2401), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2450), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2450), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2450), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2499), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2499), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2499), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2548), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2548), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2548), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2597)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 2597), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2597), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2646)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2050)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2695)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2695), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2695), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2695), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2744), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2744), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2744), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2793)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2793), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2793), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2793), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2842)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2842), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2842), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2842), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2891)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2891), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2891), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2891), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2940), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2940), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2940), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2989)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2989), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2989), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2989), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3038)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 3038), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3038), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3087)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2393)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3136), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3185)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3185), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3185), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3185), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3234)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3234), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3234), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3234), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3283)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3283), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3283), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3283), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3332), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3332), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3332), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3381)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3381), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3381), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3381), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3430)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3430), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3430), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3430), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3479)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 3479), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3479), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3577)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3577), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3577), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3577), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3626)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3626), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3626), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3626), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3675)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3675), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3675), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3675), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3724), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3724), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3724), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3773)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3773), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3773), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3773), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3822)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3822), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3822), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3822), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3871)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3871), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3871), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3871), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 3920), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3920), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3969)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 3079)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 4018)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 4018), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 4018), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[(threadIdx.x_2*12)] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 2)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 3)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 9)]
+ kernel.shared_1[((threadIdx.x_2*12) + 4)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 10)]
+ kernel.shared_1[((threadIdx.x_2*12) + 5)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 11)]
+ kernel.shared_1[((threadIdx.x_2*12) + 6)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 18)]
+ kernel.shared_1[((threadIdx.x_2*12) + 7)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 19)]
+ kernel.shared_1[((threadIdx.x_2*12) + 8)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 20)]
+ kernel.shared_1[((threadIdx.x_2*12) + 9)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 27)]
+ kernel.shared_1[((threadIdx.x_2*12) + 10)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 28)]
+ kernel.shared_1[((threadIdx.x_2*12) + 11)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 29)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ kernel.shared_1[((threadIdx.x_2*12) + 588)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 4), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 589)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 4), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 590)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 4), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 591)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 5), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 592)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 5), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 593)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 5), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 594)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 6), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 595)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 6), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 596)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 6), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 597)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 7), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 598)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 7), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 599)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 7), 64)*9)) + cse_var_1) + 2)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 30), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*12) + 1176)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 8), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1177)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 8), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1178)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 8), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1179)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 9), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1180)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 9), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1181)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 9), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1182)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 10), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1183)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 10), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1184)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 10), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1185)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 11), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1186)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 11), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1187)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 11), 64)*9)) + cse_var_1) + 2)]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ let cse_var_5: int32 = (rc.outer.inner*48)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_5]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 192)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 195)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 198)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 201)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 204)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 207)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 210)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 213)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 216)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 219)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 222)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 234)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 237)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 384)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 387)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 390)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 393)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 396)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 399)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 402)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 405)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 408)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 411)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 414)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 417)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 420)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 423)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 426)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 429)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 597)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 600)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 606)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 609)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 612)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 615)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 618)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 621)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 768)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 771)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 774)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 777)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 780)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 783)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 786)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 789)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 792)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 795)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 798)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 801)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 804)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 807)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 810)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 813)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 960)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 963)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 966)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 969)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 972)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 975)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 978)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 981)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 984)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 987)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 990)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 993)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 996)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 999)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 1002)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 1005)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 1152)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 1155)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 1158)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 1161)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 1164)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 1167)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 1170)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 1173)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 1176)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 1179)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 1182)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 1185)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 1188)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 1191)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 1194)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 1197)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 1344)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 1347)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 1350)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 1353)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 1356)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 1359)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 1362)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 1365)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 1368)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 1371)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 1374)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 1377)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 1380)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 1383)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 1386)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 1389)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 193)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 196)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 199)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 202)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 205)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 208)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 211)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 214)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 217)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 220)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 223)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 232)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 235)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 238)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 385)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 388)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 391)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 394)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 397)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 400)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 403)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 406)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 409)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 412)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 415)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 418)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 421)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 424)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 427)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 430)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 580)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 583)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 589)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 592)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 595)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 598)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 601)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 604)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 607)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 610)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 613)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 616)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 619)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 622)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 769)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 772)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 775)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 778)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 781)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 784)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 787)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 790)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 793)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 796)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 799)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 802)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 805)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 808)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 811)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 814)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 961)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 964)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 967)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 970)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 973)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 976)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 979)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 982)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 985)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 988)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 991)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 994)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 997)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 1000)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 1003)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 1006)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1153)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 1156)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 1159)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 1162)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 1165)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 1168)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 1171)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 1174)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 1177)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 1180)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 1183)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 1186)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 1189)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 1192)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 1195)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 1198)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1345)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 1348)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 1351)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 1354)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 1357)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 1360)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 1363)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 1366)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 1369)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 1372)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 1375)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 1378)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 1381)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 1384)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 1387)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 1390)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 194)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 197)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 200)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 203)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 206)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 209)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 212)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 215)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 218)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 221)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 233)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 236)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 239)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 386)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 389)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 392)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 395)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 398)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 401)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 404)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 407)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 410)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 413)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 416)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 419)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 422)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 425)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 428)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 431)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 578)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 581)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 587)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 590)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 596)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 599)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 602)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 605)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 608)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 611)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 614)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 617)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 620)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 623)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 770)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 773)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 776)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 779)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 782)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 785)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 788)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 791)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 794)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 797)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 800)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 803)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 806)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 809)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 812)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 815)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 962)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 965)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 968)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 971)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 974)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 977)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 980)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 983)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 986)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 989)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 992)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 995)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 998)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 1001)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 1004)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 1007)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 1154)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 1157)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 1160)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 1163)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 1166)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 1169)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 1172)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 1175)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 1178)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 1181)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 1184)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 1187)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 1190)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 1193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 1196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 1199)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 1346)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 1349)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 1352)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 1355)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 1358)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 1361)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 1364)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 1367)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 1370)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 1373)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 1376)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 1379)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 1382)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 1385)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 1388)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 1391)]))
}
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 208), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 224), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 272), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 304), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 352), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 368), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 400), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 416), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 464), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 496), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 544), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 560), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 592), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 608), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 656), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 688), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 736), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 752), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 8) {
+ compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
}
}
}
@@ -751,7 +899,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.348 ms
+ Execution time of this operator: 0.305 ms
@@ -796,18 +944,18 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
@@ -817,14 +965,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -842,16 +990,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=12)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -869,10 +1017,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -881,418 +1029,523 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 335)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1021)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1707)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2050)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 3079)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 14) {
+ pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[(((int)threadIdx.x) * 12)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 2)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 3)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 9)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 4)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 10)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 5)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 11)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 6)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 18)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 7)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 19)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 8)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 20)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 9)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 27)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 10)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 28)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 11)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 29)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 588)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 4) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 589)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 4) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 590)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 4) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 591)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 5) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 592)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 5) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 593)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 5) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 594)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 6) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 595)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 6) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 596)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 6) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 597)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 7) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 598)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 7) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 599)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 7) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ if (((int)threadIdx.x) < 30) {
+ kernel_shared[((((int)threadIdx.x) * 12) + 1176)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 8) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1177)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 8) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1178)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 8) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1179)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 9) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1180)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 9) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1181)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 9) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1182)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 10) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1183)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 10) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1184)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 10) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1185)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 11) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1186)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 11) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1187)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 11) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 195)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 198)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 201)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 204)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 207)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 210)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 213)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 216)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 219)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 222)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 234)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 237)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 384)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 387)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 390)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 393)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 396)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 399)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 402)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 405)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 408)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 411)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 414)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 417)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 420)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 423)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 426)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 429)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 597)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 600)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 606)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 609)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 612)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 615)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 618)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 621)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 768)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 771)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 774)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 777)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 780)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 783)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 786)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 789)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 792)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 795)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 798)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 801)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 804)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 807)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 810)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 813)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 960)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 963)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 966)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 969)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 972)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 975)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 978)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 981)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 984)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 987)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 990)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 993)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 996)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 999)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 1002)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 1005)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 1152)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 1155)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 1158)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 1161)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 1164)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 1167)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 1170)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 1173)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 1176)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 1179)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 1182)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 1185)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 1188)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 1191)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 1194)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 1197)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 1344)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 1347)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 1350)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 1353)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 1356)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 1359)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 1362)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 1365)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 1368)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 1371)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 1374)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 1377)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 1380)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 1383)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 1386)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 1389)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 193)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 196)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 199)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 202)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 205)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 208)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 211)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 214)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 217)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 220)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 223)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 232)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 235)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 238)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 385)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 388)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 391)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 394)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 397)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 400)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 403)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 406)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 409)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 412)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 415)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 418)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 421)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 424)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 427)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 430)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 580)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 583)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 589)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 592)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 595)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 598)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 601)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 604)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 607)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 610)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 613)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 616)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 619)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 622)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 769)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 772)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 775)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 778)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 781)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 784)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 787)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 790)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 793)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 796)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 799)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 802)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 805)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 808)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 811)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 814)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 961)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 964)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 967)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 970)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 973)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 976)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 979)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 982)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 985)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 988)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 991)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 994)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 997)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 1000)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 1003)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 1006)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 1153)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 1156)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 1159)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 1162)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 1165)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 1168)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 1171)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 1174)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 1177)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 1180)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 1183)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 1186)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 1189)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 1192)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 1195)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 1198)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 1345)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 1348)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 1351)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 1354)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 1357)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 1360)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 1363)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 1366)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 1369)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 1372)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 1375)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 1378)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 1381)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 1384)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 1387)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 1390)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 194)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 197)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 200)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 203)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 206)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 209)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 212)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 215)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 218)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 221)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 233)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 236)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 239)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 386)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 389)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 392)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 395)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 398)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 401)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 404)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 407)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 410)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 413)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 416)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 419)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 422)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 425)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 428)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 431)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 578)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 581)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 587)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 590)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 596)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 599)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 602)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 605)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 608)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 611)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 614)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 617)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 620)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 623)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 770)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 773)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 776)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 779)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 782)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 785)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 788)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 791)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 794)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 797)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 800)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 803)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 806)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 809)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 812)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 815)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 962)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 965)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 968)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 971)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 974)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 977)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 980)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 983)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 986)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 989)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 992)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 995)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 998)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 1001)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 1004)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 1007)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 1154)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 1157)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 1160)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 1163)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 1166)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 1169)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 1172)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 1175)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 1178)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 1181)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 1184)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 1187)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 1190)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 1193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 1196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 1199)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 1346)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 1349)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 1352)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 1355)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 1358)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 1361)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 1364)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 1367)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 1370)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 1373)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 1376)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 1379)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 1382)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 1385)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 1388)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 1391)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1351,7 +1604,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 33.953 seconds)
+ **Total running time of the script:** ( 2 minutes 35.151 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
index dd420d69d..aa5bc87cc 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -616,7 +616,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.4903 9.4911 9.4979 9.4817 0.0066
+ 9.7428 9.7631 9.7740 9.6913 0.0367
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index 54b535cef..c4e068b03 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -635,7 +635,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 761.6862 761.8040 761.9038 761.3507 0.2407
+ 749.8626 750.5058 751.4467 747.6353 1.6211
@@ -660,7 +660,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.230 seconds)
+ **Total running time of the script:** ( 1 minutes 20.213 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_x86.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
index 49b9fde90..9b48b5605 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -362,78 +362,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 64) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ if let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_4: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_4]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_4] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_5: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_5, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_5, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -487,7 +439,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.861 ms
+ Execution time of this operator: 1.474 ms
diff --git a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
index 709b14e8b..f75be8411 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.994** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.137** total execution time for **how_to_tune_with_autotvm** files:
-- **00:44.072**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.239**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.224**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:43.278**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.228**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.213**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.211**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.209**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index bb296fbff..e2c9ea3fa 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 112.37/112.37 result: MeasureResult(costs=(0.002060116727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8840768337249756, timestamp=1654838616.8286886) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 103.31/103.31 result: MeasureResult(costs=(0.0022409267291666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.614325761795044, timestamp=1654841523.1741066) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f13b4e4dfa2
+ 12: 0x00007fccb28c4fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 144.09/144.09 result: MeasureResult(costs=(0.00160667445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.433812141418457, timestamp=1654838643.375321) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 143.90/143.90 result: MeasureResult(costs=(0.00160881471,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4116015434265137, timestamp=1654841549.5921435) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.001996
+ Time cost of this operator: 0.001997
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
index cdceae978..8795ce01d 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -294,10 +294,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.2 98.767 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.946 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.915 0.287 (1, 1, 10, 10, 3) 1 1
- Total_time - 319.136 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.8 98.741 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.967 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.928 0.292 (1, 1, 10, 10, 3) 1 1
+ Total_time - 317.801 - - - -
@@ -359,10 +359,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 328.3 98.778 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.134 0.943 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.927 0.279 (1, 1, 10, 10, 3) 1 1
- Total_time - 332.361 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 227.9 98.789 (1, 1, 10, 10, 6) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.973 0.855 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.821 0.356 (1, 3, 10, 10, 1) 1 1
+ Total_time - 230.694 - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 228a48539..972f76fc6 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -297,8 +297,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpaqr8poau/images/target contains 8144 images
- /tmp/tmpaqr8poau/images/random contains 5000 images
+ /tmp/tmpzle21gp8/images/target contains 8144 images
+ /tmp/tmpzle21gp8/images/random contains 5000 images
@@ -459,11 +459,11 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 54s - loss: 0.2182 - accuracy: 0.9275 - val_loss: 0.1462 - val_accuracy: 0.9558
+ 328/328 - 54s - loss: 0.2550 - accuracy: 0.9161 - val_loss: 0.1391 - val_accuracy: 0.9554
Epoch 2/3
- 328/328 - 52s - loss: 0.0988 - accuracy: 0.9627 - val_loss: 0.1110 - val_accuracy: 0.9615
+ 328/328 - 52s - loss: 0.0980 - accuracy: 0.9617 - val_loss: 0.1138 - val_accuracy: 0.9634
Epoch 3/3
- 328/328 - 52s - loss: 0.0669 - accuracy: 0.9751 - val_loss: 0.1186 - val_accuracy: 0.9619
+ 328/328 - 52s - loss: 0.0696 - accuracy: 0.9740 - val_loss: 0.1179 - val_accuracy: 0.9641
@@ -825,7 +825,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 9.487 seconds)
+ **Total running time of the script:** ( 4 minutes 22.020 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 5c6d806c7..c065df140 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**04:56.585** total execution time for **how_to_work_with_microtvm** files:
-
-- **04:09.487**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)
-- **00:42.794**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.688**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.214**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.202**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.199**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+**05:07.590** total execution time for **how_to_work_with_microtvm** files:
+
+- **04:22.020**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)
+- **00:41.441**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.547**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.197**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.194**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.191**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 19cd5c1ca..b8b0f2eb6 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:12.012** total execution time for **how_to_work_with_relay** files:
+**00:10.172** total execution time for **how_to_work_with_relay** files:
-- **00:10.034**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.751**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.226**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:08.278**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.682**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.212**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
index d099fe3bc..4c4b2cfe4 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.757** total execution time for **how_to_work_with_schedules** files:
+**00:05.589** total execution time for **how_to_work_with_schedules** files:
-- **00:02.103**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.117**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.746**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.733**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.324**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.259**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.242**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.232**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.039**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.179**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.708**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.696**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.296**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.230**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.226**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.215**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 68473cf27..ff90c14c5 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -318,7 +318,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpp40fggce/input0.cc'\nsource_filename = \"/tmp/tmpp40fggce/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpeox3jqg9/input0.cc'\nsource_filename = \"/tmp/tmpeox3jqg9/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 5358d79c4..940043cb1 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:21.460** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.868** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:21.239**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.222**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.658**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.209**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 9bd86c724..6cbbd6a52 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -267,7 +267,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.73s!
+ resnet18_v1 inference graph built in 21.79s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
index fa6d510f1..91a42fdc4 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -303,7 +303,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.81s!
+ yolov3-tiny inference graph built in 15.34s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index d84b2e480..51e378fa7 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**01:31.475** total execution time for **topic_vta_tutorials_frontend** files:
+**01:29.978** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:48.054**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:43.421**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:47.832**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:42.146**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index f18831ae2..cdf98ef7a 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.660** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.596** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.069**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.591**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:03.009**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.587**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index f26d0bf83..1e30153ec 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.112** total execution time for **topic_vta_tutorials** files:
+**00:01.067** total execution time for **topic_vta_tutorials** files:
-- **00:00.570**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.542**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.546**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.521**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 9227a22c4..a37748091 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -185,7 +185,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
-
+ *E
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.741 ms
+ Execution time of this operator: 93.189 ms
@@ -402,7 +402,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ .T
@@ -415,6 +415,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 10.425 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 74bb3f032..653e3a405 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -280,7 +280,7 @@ standard deviation.
.. code-block:: none
- {'mean': 495.74220690999937, 'median': 495.29935435000425, 'std': 1.3625708524781053}
+ {'mean': 493.39824311000484, 'median': 493.2903070499833, 'std': 0.47540514005182377}
@@ -494,31 +494,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.38/ 17.38 GFLOPS | Progress: (4/20) | 6.10 s
[Task 1/25] Current/Best: 6.15/ 17.38 GFLOPS | Progress: (8/20) | 9.07 s
[Task 1/25] Current/Best: 11.50/ 22.83 GFLOPS | Progress: (12/20) | 11.54 s
[Task 1/25] Current/Best: 16.76/ 22.83 GFLOPS | Progress: (16/20) | 13.22 s
[Task 1/25] Current/Best: 11.61/ 23.88 GFLOPS | Progress: (20/20) | 14.96 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.28/ 12.96 GFLOPS | Progress: (4/20) | 3.75 s
[Task 2/25] Current/Best: 13.03/ 18.05 GFLOPS | Progress: (8/20) | 5.04 s
[Task 2/25] Current/Best: 21.11/ 21.11 GFLOPS | Progress: (12/20) | 6.38 s
[Task 2/25] Current/Best: 12.77/ 21.11 GFLOPS | Progress: (16/20) | 7.68 s
[Task 2/25] Current/Best: 19.76/ 21.11 GFLOPS | Progress: (20/20) | 9.28 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.49 GFLOPS | Progress: (4/20) | 5.81 s
[Task 3/25] Current/Best: 15.54/ 16.89 GFLOPS | Progress: (8/20) | 7.74 s
[Task 3/25] Current/Best: 14.90/ 16.89 GFLOPS | Progress: (12/20) | 9.46 s
[Task 3/25] Current/Best: 7.14/ 23.69 GFLOPS | Progress: (16/20) | 11.40 s
[Task 3/25] Current/Best: 12.60/ 23.69 GFLOPS | Progress: (20/20) | 16.00 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.49/ 20.33 GFLOPS | Progress: (4/20) | 2.33 s
[Task 4/25] Current/Best: 6.87/ 20.33 GFLOPS | Progress: (8/20) | 7.10 s
[Task 4/25] Current/Best: 21.93/ 21.93 GFLOPS | Progress: (12/20) | 12.05 s
[Task 4/25] Current/Best: 17.26/ 21.93 GFLOPS | Progress: (16/20) | 14.47 s
[Task 4/25] Current/Best: 13.05/ 21.93 GFLOPS | Progress: (20/20) | 16.46 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.58/ 10.38 GFLOPS | Progress: (4/20) | 2.53 s
[Task 5/25] Current/Best: 11.82/ 12.60 GFLOPS | Progress: (8/20) | 4.60 s
[Task 5/25] Current/Best: 10.52/ 17.96 GFLOPS | Progress: (12/20) | 7.79 s
[Task 5/25] Current/Best: 11.59/ 22.44 GFLOPS | Progress: (16/20) | 9.25 s
[Task 5/25] Current/Best: 11.96/ 22.44 GFLOPS | Progress: (20/20) | 11.15 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.23/ 20.72 GFLOPS | Progress: (4/20) | 4.07 s
[Task 6/25] Current/Best: 18.98/ 20.72 GFLOPS | Progress: (8/20) | 5.85 s
[Task 6/25] Current/Best: 13.31/ 20.72 GFLOPS | Progress: (12/20) | 7.82 s
[Task 6/25] Current/Best: 20.03/ 20.72 GFLOPS | Progress: (16/20) | 10.05 s
[Task 6/25] Current/Best: 3.72/ 20.72 GFLOPS | Progress: (20/20) | 12.55 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.14/ 12.75 GFLOPS | Progress: (4/20) | 3.59 s
[Task 7/25] Current/Best: 20.20/ 21.13 GFLOPS | Progress: (8/20) | 5.10 s
[Task 7/25] Current/Best: 15.28/ 21.13 GFLOPS | Progress: (12/20) | 7.03 s
[Task 7/25] Current/Best: 12.21/ 21.13 GFLOPS | Progress: (16/20) | 9.09 s
[Task 7/25] Current/Best: 6.37/ 21.72 GFLOPS | Progress: (20/20) | 11.54 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.02/ 14.31 GFLOPS | Progress: (4/20) | 2.84 s
[Task 8/25] Current/Best: 9.52/ 14.31 GFLOPS | Progress: (8/20) | 8.04 s
[Task 8/25] Current/Best: 13.28/ 14.31 GFLOPS | Progress: (12/20) | 14.64 s
[Task 8/25] Current/Best: 18.67/ 18.67 GFLOPS | Progress: (16/20) | 16.71 s
[Task 8/25] Current/Best: 19.64/ 19.64 GFLOPS | Progress: (20/20) | 23.87 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.26/ 15.56 GFLOPS | Progress: (4/20) | 11.91 s
[Task 9/25] Current/Best: 23.51/ 23.51 GFLOPS | Progress: (8/20) | 13.66 s
[Task 9/25] Current/Best: 8.20/ 23.51 GFLOPS | Progress: (12/20) | 16.23 s
[Task 9/25] Current/Best: 17.88/ 23.51 GFLOPS | Progress: (16/20) | 19.14 s
[Task 9/25] Current/Best: 8.96/ 23.51 GFLOPS | Progress: (20/20) | 27.99 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.29/ 18.29 GFLOPS | Progress: (4/20) | 2.53 s
[Task 10/25] Current/Best: 15.44/ 18.29 GFLOPS | Progress: (8/20) | 4.22 s
[Task 10/25] Current/Best: 12.52/ 18.87 GFLOPS | Progress: (12/20) | 5.76 s
[Task 10/25] Current/Best: 19.07/ 20.26 GFLOPS | Progress: (16/20) | 6.87 s
[Task 10/25] Current/Best: 8.74/ 20.26 GFLOPS | Progress: (20/20
) | 8.40 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.76/ 18.09 GFLOPS | Progress: (4/20) | 3.33 s
[Task 11/25] Current/Best: 16.99/ 18.09 GFLOPS | Progress: (8/20) | 6.19 s
[Task 11/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (12/20) | 8.27 s
[Task 11/25] Current/Best: 13.46/ 21.17 GFLOPS | Progress: (16/20) | 11.24 s
[Task 11/25] Current/Best: 19.45/ 21.55 GFLOPS | Progress: (20/20) | 13.36 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.75/ 18.36 GFLOPS | Progress: (4/20) | 5.80 s
[Task 12/25] Current/Best: 5.28/ 18.36 GFLOPS | Progress: (8/20) | 9.77 s
[Task 12/25] Current/Best: 18.93/ 19.05 GFLOPS | Progress: (12/20) | 11.76 s
[Task 12/25] Current/Best: 15.26/ 19.05 GFLOPS | Progress: (16/20) | 14.74 s
[Task 12/25] Current/Best: 15.18/ 19.05 GFLOPS | Progress: (20/20) | 16.67 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.88/ 17.20 GFLOPS | Progress: (4/20) | 3.68 s
[Task 13/25] Current/Best: 15.63/ 20.78 GFLOPS | Progress: (8/20) | 6.33 s
[Task 13/25] Current/Best: 19.51/ 21.83 GFLOPS | Progress: (12/20) | 9.41 s
[Task 13/25] Current/Best: 12.23/ 21.83 GFLOPS | Progress: (16/20) | 12.83 s
[Task 13/25] Current/Best: 18.72/ 21.83 GFLOPS | Progress: (20/20) | 15.20 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.52/ 13.52 GFLOPS | Progress: (4/20) | 3.36 s
[Task 14/25] Current/Best: 6.10/ 13.52 GFLOPS | Progress: (8/20) | 5.59 s
[Task 14/25] Current/Best: 20.35/ 20.35 GFLOPS | Progress: (12/20) | 8.32 s
[Task 14/25] Current/Best: 17.38/ 20.35 GFLOPS | Progress: (16/20) | 9.99 s Done.
-
[Task 14/25] Current/Best: 17.01/ 20.35 GFLOPS | Progress: (20/20) | 11.74 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.18/ 17.65 GFLOPS | Progress: (4/20) | 2.66 s
[Task 15/25] Current/Best: 14.21/ 18.15 GFLOPS | Progress: (8/20) | 3.96 s
[Task 15/25] Current/Best: 10.38/ 21.53 GFLOPS | Progress: (12/20) | 6.25 s
[Task 15/25] Current/Best: 20.43/ 21.53 GFLOPS | Progress: (16/20) | 9.86 s
[Task 15/25] Current/Best: 9.69/ 21.53 GFLOPS | Progress: (20/20) | 10.87 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (4/20) | 2.89 s
[Task 16/25] Current/Best: 3.04/ 20.85 GFLOPS | Progress: (8/20) | 4.51 s
[Task 16/25] Current/Best: 19.61/ 20.85 GFLOPS | Progress: (12/20) | 5.73 s
[Task 16/25] Current/Best: 17.79/ 20.85 GFLOPS | Progress: (16/20) |
7.10 s
[Task 16/25] Current/Best: 9.92/ 22.27 GFLOPS | Progress: (20/20) | 9.29 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.40/ 18.89 GFLOPS | Progress: (4/20) | 4.75 s
[Task 17/25] Current/Best: 14.37/ 23.35 GFLOPS | Progress: (8/20) | 7.66 s
[Task 17/25] Current/Best: 17.08/ 23.35 GFLOPS | Progress: (12/20) | 9.72 s
[Task 17/25] Current/Best: 16.48/ 23.35 GFLOPS | Progress: (16/20) | 11.96 s
[Task 17/25] Current/Best: 10.02/ 23.35 GFLOPS | Progress: (20/20) | 14.13 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.41/ 17.90 GFLOPS | Progress: (4/20) | 3.79 s
[Task 18/25] Current/Best: 10.54/ 19.94 GFLOPS | Progress: (8/20) | 7.52 s
[Task 18/25] Current/Best: 19.34/ 19.94 GFLOPS | Progress: (12/20) | 9.47 s
[Task 18/25] Current/Best: 9.88/ 19.94 GFLOPS | Progress: (16/20) | 13.40 s
[Task 18/25] Current/Best: 20.57/ 20.57 GFLOPS | Progress: (20/20) | 14.93 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.67/ 20.23 GFLOPS | Progress: (4/20) | 6.16 s
[Task 19/25] Current/Best: 2.60/ 20.23 GFLOPS | Progress: (8/20) | 9.50 s
[Task 19/25] Current/Best: 19.80/ 21.62 GFLOPS | Progress: (12/20) | 12.54 s
[Task 19/25] Current/Best: 15.25/ 21.62 GFLOPS | Progress: (16/20) | 15.57 s
[Task 19/25] Current/Best: 2.70/ 23.03 GFLOPS | Progress: (20/20) | 18.34 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.78/ 14.91 GFLOPS | Progress: (4/20) | 3.32 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (4/20) | 6.00 s
[Task 1/25] Current/Best: 6.17/ 17.49 GFLOPS | Progress: (8/20) | 8.83 s
[Task 1/25] Current/Best: 11.57/ 22.64 GFLOPS | Progress: (12/20) | 11.29 s
[Task 1/25] Current/Best: 16.87/ 22.88 GFLOPS | Progress: (16/20) | 12.96 s
[Task 1/25] Current/Best: 11.62/ 23.86 GFLOPS | Progress: (20/20) | 14.67 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.20/ 13.22 GFLOPS | Progress: (4/20) | 3.77 s
[Task 2/25] Current/Best: 14.20/ 18.27 GFLOPS | Progress: (8/20) | 5.08 s
[Task 2/25] Current/Best: 20.24/ 20.24 GFLOPS | Progress: (12/20) | 6.41 s
[Task 2/25] Current/Best: 12.63/ 20.24 GFLOPS | Progress: (16/20) | 7.65 s
[Task 2/25] Current/Best: 18.91/ 20.24 GFLOPS | Progress: (20/20) | 9.24 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.54 GFLOPS | Progress: (4/20) | 5.76 s
[Task 3/25] Current/Best: 15.60/ 16.92 GFLOPS | Progress: (8/20) | 7.69 s
[Task 3/25] Current/Best: 14.92/ 16.92 GFLOPS | Progress: (12/20) | 9.39 s
[Task 3/25] Current/Best: 7.24/ 23.80 GFLOPS | Progress: (16/20) | 11.28 s
[Task 3/25] Current/Best: 11.22/ 23.80 GFLOPS | Progress: (20/20) | 15.83 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.45 GFLOPS | Progress: (4/20) | 2.29 s
[Task 4/25] Current/Best: 6.86/ 20.45 GFLOPS | Progress: (8/20) | 6.94 s
[Task 4/25] Current/Best: 22.46/ 22.46 GFLOPS | Progress: (12/20) | 11.86 s
[Task 4/25] Current/Best: 17.42/ 22.46 GFLOPS | Progress: (16/20) | 14.21 s
[Task 4/25] Current/Best: 13.63/ 22.46 GFLOPS | Progress: (20/20) | 16.16 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.53/ 10.30 GFLOPS | Progress: (4/20) | 2.49 s
[Task 5/25] Current/Best: 11.68/ 12.76 GFLOPS | Progress: (8/20) | 4.54 s
[Task 5/25] Current/Best: 11.72/ 18.04 GFLOPS | Progress: (12/20) | 7.71 s
[Task 5/25] Current/Best: 11.73/ 22.56 GFLOPS | Progress: (16/20) | 9.12 s
[Task 5/25] Current/Best: 12.07/ 22.56 GFLOPS | Progress: (20/20) | 11.02 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.23/ 20.75 GFLOPS | Progress: (4/20) | 3.99 s
[Task 6/25] Current/Best: 19.02/ 20.75 GFLOPS | Progress: (8/20) | 5.74 s
[Task 6/25] Current/Best: 13.12/ 20.75 GFLOPS | Progress: (12/20) | 7.68 s
[Task 6/25] Current/Best: 20.04/ 20.75 GFLOPS | Progress: (16/20) | 9.91 s
[Task 6/25] Current/Best: 3.72/ 20.75 GFLOPS | Progress: (20/20) | 12.43 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.04/ 12.90 GFLOPS | Progress: (4/20) | 3.48 s
[Task 7/25] Current/Best: 20.28/ 21.10 GFLOPS | Progress: (8/20) | 4.99 s
[Task 7/25] Current/Best: 16.07/ 21.10 GFLOPS | Progress: (12/20) | 6.87 s
[Task 7/25] Current/Best: 12.27/ 21.10 GFLOPS | Progress: (16/20) | 8.90 s
[Task 7/25] Current/Best: 6.26/ 21.96 GFLOPS | Progress: (20/20) | 11.34 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.61/ 13.50 GFLOPS | Progress: (4/20) | 2.84 s
[Task 8/25] Current/Best: 9.30/ 13.50 GFLOPS | Progress: (8/20) | 7.97 s
[Task 8/25] Current/Best: 12.23/ 13.50 GFLOPS | Progress: (12/20) | 14.37 s
[Task 8/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (16/20) | 16.50 s
[Task 8/25] Current/Best: 20.04/ 20.04 GFLOPS | Progress: (20/20) | 23.48 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.32/ 15.73 GFLOPS | Progress: (4/20) | 11.88 s
[Task 9/25] Current/Best: 23.42/ 23.42 GFLOPS | Progress: (8/20) | 13.57 s
[Task 9/25] Current/Best: 8.28/ 23.42 GFLOPS | Progress: (12/20) | 16.06 s
[Task 9/25] Current/Best: 17.96/ 23.42 GFLOPS | Progress: (16/20) | 18.87 s
[Task 9/25] Current/Best: 9.08/ 23.42 GFLOPS | Progress: (20/20) | 27.42 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.17/ 18.17 GFLOPS | Progress: (4/20) | 2.46 s
[Task 10/25] Current/Best: 15.52/ 18.17 GFLOPS | Progress: (8/20) | 4.07 s
[Task 10/25] Current/Best: 12.73/ 18.86 GFLOPS | Progress: (12/20) | 5.60 s
[Task 10/25] Current/Best: 19.23/ 20.25 GFLOPS | Progress: (16/20) | 6.69 s
[Task 10/25] Current/Best: 8.83/ 20.25 GFLOPS | Progress: (20/20
) | 8.22 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.08/ 18.12 GFLOPS | Progress: (4/20) | 3.26 s
[Task 11/25] Current/Best: 16.95/ 18.12 GFLOPS | Progress: (8/20) | 6.05 s
[Task 11/25] Current/Best: 17.81/ 18.12 GFLOPS | Progress: (12/20) | 8.12 s
[Task 11/25] Current/Best: 13.15/ 21.19 GFLOPS | Progress: (16/20) | 10.96 s
[Task 11/25] Current/Best: 19.50/ 21.58 GFLOPS | Progress: (20/20) | 13.05 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.82/ 18.16 GFLOPS | Progress: (4/20) | 5.62 s
[Task 12/25] Current/Best: 5.13/ 18.16 GFLOPS | Progress: (8/20) | 9.50 s
[Task 12/25] Current/Best: 18.75/ 19.00 GFLOPS | Progress: (12/20) | 11.48 s
[Task 12/25] Current/Best: 15.41/ 19.00 GFLOPS | Progress: (16/20) | 14.38 s
[Task 12/25] Current/Best: 15.14/ 19.00 GFLOPS | Progress: (20/20) | 16.33 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 7.77/ 17.29 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 15.47/ 20.97 GFLOPS | Progress: (8/20) | 6.24 s
[Task 13/25] Current/Best: 19.58/ 20.97 GFLOPS | Progress: (12/20) | 9.31 s
[Task 13/25] Current/Best: 12.28/ 20.97 GFLOPS | Progress: (16/20) | 12.69 s
[Task 13/25] Current/Best: 18.66/ 20.97 GFLOPS | Progress: (20/20) | 14.96 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.54/ 13.54 GFLOPS | Progress: (4/20) | 3.33 s
[Task 14/25] Current/Best: 6.11/ 13.54 GFLOPS | Progress: (8/20) | 5.56 s
[Task 14/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (12/20) | 8.22 s
[Task 14/25] Current/Best: 16.25/ 20.48 GFLOPS | Progress: (16/20) | 9.86 s Done.
+
[Task 14/25] Current/Best: 17.34/ 20.48 GFLOPS | Progress: (20/20) | 11.57 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.17/ 17.63 GFLOPS | Progress: (4/20) | 2.59 s
[Task 15/25] Current/Best: 14.36/ 18.14 GFLOPS | Progress: (8/20) | 3.88 s
[Task 15/25] Current/Best: 10.40/ 22.32 GFLOPS | Progress: (12/20) | 6.08 s
[Task 15/25] Current/Best: 20.41/ 22.32 GFLOPS | Progress: (16/20) | 9.77 s
[Task 15/25] Current/Best: 9.71/ 22.32 GFLOPS | Progress: (20/20) | 10.78 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (4/20) | 2.81 s
[Task 16/25] Current/Best: 3.04/ 19.77 GFLOPS | Progress: (8/20) | 4.40 s
[Task 16/25] Current/Best: 18.91/ 19.77 GFLOPS | Progress: (12/20) | 5.60 s
[Task 16/25] Current/Best: 17.91/ 19.77 GFLOPS | Progress: (16/20) |
6.98 s
[Task 16/25] Current/Best: 10.04/ 22.29 GFLOPS | Progress: (20/20) | 9.11 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.08/ 18.84 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 13.71/ 23.42 GFLOPS | Progress: (8/20) | 7.56 s
[Task 17/25] Current/Best: 16.90/ 23.42 GFLOPS | Progress: (12/20) | 9.59 s
[Task 17/25] Current/Best: 16.51/ 23.42 GFLOPS | Progress: (16/20) | 11.79 s
[Task 17/25] Current/Best: 10.03/ 23.42 GFLOPS | Progress: (20/20) | 13.92 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.14/ 17.41 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 10.58/ 20.16 GFLOPS | Progress: (8/20) | 7.38 s
[Task 18/25] Current/Best: 19.38/ 20.16 GFLOPS | Progress: (12/20) | 9.29 s
[Task 18/25] Current/Best: 10.04/ 20.16 GFLOPS | Progress: (16/20) | 13.11 s
[Task 18/25] Current/Best: 20.83/ 20.83 GFLOPS | Progress: (20/20) | 14.60 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.16/ 20.48 GFLOPS | Progress: (4/20) | 6.01 s
[Task 19/25] Current/Best: 2.60/ 20.48 GFLOPS | Progress: (8/20) | 9.42 s
[Task 19/25] Current/Best: 20.28/ 21.94 GFLOPS | Progress: (12/20) | 12.41 s
[Task 19/25] Current/Best: 14.15/ 21.94 GFLOPS | Progress: (16/20) | 15.45 s
[Task 19/25] Current/Best: 2.70/ 23.58 GFLOPS | Progress: (20/20) | 18.30 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.87/ 15.30 GFLOPS | Progress: (4/20) | 3.27 s Done.
Done.
-
[Task 20/25] Current/Best: 10.15/ 14.91 GFLOPS | Progress: (8/20) | 6.76 s
[Task 20/25] Current/Best: 2.32/ 16.55 GFLOPS | Progress: (12/20) | 10.75 s
[Task 20/25] Current/Best: 12.39/ 16.55 GFLOPS | Progress: (16/20) | 14.54 s
[Task 20/25] Current/Best: 13.36/ 21.94 GFLOPS | Progress: (20/20) | 16.66 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.30/ 17.72 GFLOPS | Progress: (4/20) | 3.26 s
[Task 21/25] Current/Best: 14.41/ 17.72 GFLOPS | Progress: (8/20) | 4.90 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 7.02 s
[Task 21/25] Current/Best: 16.58/ 17.72 GFLOPS | Progress: (16/20) | 10.56 s
[Task 21/25] Current/Best: 4.47/ 17.72 GFLOPS | Progress: (20/20) | 18.01 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.89 GFLOPS | Progress: (4/20
) | 2.65 s
[Task 22/25] Current/Best: 9.21/ 21.17 GFLOPS | Progress: (8/20) | 4.64 s
[Task 22/25] Current/Best: 19.96/ 21.17 GFLOPS | Progress: (12/20) | 7.07 s
[Task 22/25] Current/Best: 14.69/ 21.17 GFLOPS | Progress: (16/20) | 9.21 s
[Task 22/25] Current/Best: 14.25/ 21.17 GFLOPS | Progress: (20/20) | 10.89 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.39/ 20.24 GFLOPS | Progress: (4/20) | 3.19 s
[Task 23/25] Current/Best: 15.79/ 20.24 GFLOPS | Progress: (8/20) | 6.50 s
[Task 23/25] Current/Best: 20.88/ 21.63 GFLOPS | Progress: (12/20) | 8.35 s
[Task 23/25] Current/Best: 6.26/ 21.63 GFLOPS | Progress: (16/20) | 15.60 s
[Task 23/25] Current/Best: 7.73/ 21.63 GFLOPS | Progress: (20/20) | 19.89 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.52/ 8.52 GFLOPS | Progress: (4/20) | 11.74 s
[Task 24/25] Current/Best: 1.89/ 8.52 GFLOPS | Progress: (8/20) | 22.76 s
[Task 24/25] Current/Best: 4.40/ 8.52 GFLOPS | Progress: (12/20) | 34.25 s Done.
+
[Task 20/25] Current/Best: 10.14/ 15.30 GFLOPS | Progress: (8/20) | 6.63 s
[Task 20/25] Current/Best: 2.32/ 16.52 GFLOPS | Progress: (12/20) | 10.54 s
[Task 20/25] Current/Best: 12.25/ 16.52 GFLOPS | Progress: (16/20) | 14.41 s
[Task 20/25] Current/Best: 12.35/ 22.39 GFLOPS | Progress: (20/20) | 16.50 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.68 GFLOPS | Progress: (4/20) | 3.19 s
[Task 21/25] Current/Best: 14.61/ 17.68 GFLOPS | Progress: (8/20) | 4.76 s
[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 6.85 s
[Task 21/25] Current/Best: 18.02/ 18.02 GFLOPS | Progress: (16/20) | 10.29 s
[Task 21/25] Current/Best: 4.47/ 18.02 GFLOPS | Progress: (20/20) | 17.52 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.71/ 16.97 GFLOPS | Progress: (4/20
) | 2.59 s
[Task 22/25] Current/Best: 8.62/ 21.97 GFLOPS | Progress: (8/20) | 4.61 s
[Task 22/25] Current/Best: 19.99/ 21.97 GFLOPS | Progress: (12/20) | 7.00 s
[Task 22/25] Current/Best: 15.24/ 21.97 GFLOPS | Progress: (16/20) | 9.09 s
[Task 22/25] Current/Best: 13.94/ 21.97 GFLOPS | Progress: (20/20) | 10.82 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.66/ 20.90 GFLOPS | Progress: (4/20) | 3.17 s
[Task 23/25] Current/Best: 14.02/ 20.90 GFLOPS | Progress: (8/20) | 6.55 s
[Task 23/25] Current/Best: 21.03/ 21.63 GFLOPS | Progress: (12/20) | 8.38 s
[Task 23/25] Current/Best: 6.45/ 21.63 GFLOPS | Progress: (16/20) | 15.35 s
[Task 23/25] Current/Best: 7.89/ 21.63 GFLOPS | Progress: (20/20) | 19.53 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.52/ 8.52 GFLOPS | Progress: (4/20) | 11.71 s
[Task 24/25] Current/Best: 3.72/ 8.52 GFLOPS | Progress: (8/20) | 22.88 s
[Task 24/25] Current/Best: 4.40/ 8.52 GFLOPS | Progress: (12/20) | 33.59 s Done.
Done.
-
[Task 24/25] Current/Best: 7.11/ 8.82 GFLOPS | Progress: (16/20) | 40.10 s
[Task 24/25] Current/Best: 3.32/ 9.07 GFLOPS | Progress: (20/20) | 46.08 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.84 GFLOPS | Progress: (4/20) | 11.58 s
[Task 25/25] Current/Best: 5.51/ 7.83 GFLOPS | Progress: (8/20) | 22.82 s
[Task 25/25] Current/Best: 5.92/ 7.83 GFLOPS | Progress: (12/20) | 34.08 s
[Task 25/25] Current/Best: 5.75/ 9.53 GFLOPS | Progress: (16/20) | 35.95 s
[Task 25/25] Current/Best: 2.85/ 9.53 GFLOPS | Progress: (20/20) | 46.66 s
+
[Task 24/25] Current/Best: 6.05/ 8.88 GFLOPS | Progress: (16/20) | 39.24 s
[Task 24/25] Current/Best: 3.29/ 8.94 GFLOPS | Progress: (20/20) | 45.27 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.74 GFLOPS | Progress: (4/20) | 11.52 s
[Task 25/25] Current/Best: 6.21/ 8.19 GFLOPS | Progress: (8/20) | 22.71 s
[Task 25/25] Current/Best: 6.06/ 8.19 GFLOPS | Progress: (12/20) | 34.13 s
[Task 25/25] Current/Best: 5.96/ 8.96 GFLOPS | Progress: (16/20) | 35.93 s
[Task 25/25] Current/Best: 2.85/ 8.96 GFLOPS | Progress: (20/20) | 46.64 s
The output from this tuning process will look something like this:
@@ -660,8 +660,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 406.64832210999066, 'median': 406.6049121499873, 'std': 0.9916208581321372}
- unoptimized: {'mean': 495.74220690999937, 'median': 495.29935435000425, 'std': 1.3625708524781053}
+ optimized: {'mean': 408.2465482099951, 'median': 407.9875301500124, 'std': 0.7929834703939768}
+ unoptimized: {'mean': 493.39824311000484, 'median': 493.2903070499833, 'std': 0.47540514005182377}
@@ -681,7 +681,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 26.059 seconds)
+ **Total running time of the script:** ( 10 minutes 16.231 seconds)
.. _sphx_glr_download_tutorial_autotvm_relay_x86.py:
diff --git a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
index 74cb7f80d..4e2b5d3ba 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.327e-07 secs/op
+ 1.307e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index eb0be4bdb..fe9eefc65 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -232,7 +232,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x22a1e580)), stage(b, placeholder(b, 0x21e54820)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x21d96dc0)), stage(b, placeholder(b, 0x240d9970)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 9cd4eb056..c099991f5 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**13:04.888** total execution time for **tutorial** files:
+**13:20.062** total execution time for **tutorial** files:
-- **10:26.059**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:00.193**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:44.997**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:28.514**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:23.380**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:00.738**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.596**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.215**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.051**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.051**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.048**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.045**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **10:16.231**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:10.425**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **01:00.705**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:27.823**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:23.310**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.710**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.546**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.183**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.034**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.033**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.031**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.031**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 0986f0e82..60d6cecec 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -344,7 +344,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000009
+ parallel: 0.000006
@@ -447,10 +447,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.191320002879365e-06 1.0
- naive 5.8477e-06 0.7138898245880335
- parallel 9.073599999999999e-06 1.107709135622891
- vector 2.45916e-05 3.0021534980144473
+ numpy 7.999680001375964e-06 1.0
+ naive 5.816000000000001e-06 0.727029081038196
+ parallel 6.0257e-06 0.7532426295756287
+ vector 2.45517e-05 3.0690852628826466
@@ -839,7 +839,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019101
+ Numpy running time: 0.017842
@@ -897,7 +897,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.301316
+ none: 3.415635
@@ -996,7 +996,7 @@ schedule.
.. code-block:: none
- blocking: 0.312972
+ blocking: 0.296504
@@ -1088,7 +1088,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.347309
+ vectorization: 0.332314
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1160,7 +1160,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116958
+ loop permutation: 0.115560
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1257,7 +1257,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109094
+ array packing: 0.108832
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1348,7 +1348,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111109
+ block caching: 0.110441
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1432,7 +1432,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.144448
+ parallelization: 0.144405
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1511,13 +1511,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3013155026 1.0
- blocking 0.31297230490000005 0.0948023006748413
- vectorization 0.3473088062 0.10520315490187829
- loop permutation 0.1169579685 0.03542768584459377
- array packing 0.1090935009 0.03304546348692871
- block caching 0.11110894089999998 0.03365595951447067
- parallelization 0.14444780929999998 0.04375462120667896
+ none 3.4156349571999995 1.0
+ blocking 0.2965043973 0.08680798768468584
+ vectorization 0.3323138368 0.0972919650267362
+ loop permutation 0.1155596145 0.03383254239637222
+ array packing 0.10883164409999999 0.031862785532917666
+ block caching 0.1104411021 0.03233398869723923
+ parallelization 0.14440524419999998 0.04227771585941889
@@ -1554,7 +1554,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.193 seconds)
+ **Total running time of the script:** ( 1 minutes 0.705 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index dbfaeb7d0..82b0c23e2 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-ec24ae60a028f5aae0fa2f1d8a668eb6bf366414
+6fca5c657a2fadc16fd7ff44de8a6a9656d50c1b
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 0c7a6c46c..782eb1d4d 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb9a21007-85fe-4ff4-bf19-98da9769e6be from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip5772ac00-f1cd-4fd2-87d6-a521d7e88b81 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index 25c538655..f7dcc8634 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,43 +406,105 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<08:11, 88.5kB/s]
- 0%| | 48.0k/41.5M [00:00<05:09, 140kB/s]
- 0%| | 104k/41.5M [00:00<03:20, 217kB/s]
- 0%| | 208k/41.5M [00:00<02:01, 358kB/s]
- 1%| | 424k/41.5M [00:00<01:05, 658kB/s]
- 2%|2 | 864k/41.5M [00:01<00:33, 1.26MB/s]
- 4%|4 | 1.70M/41.5M [00:01<00:17, 2.42MB/s]
- 7%|6 | 2.88M/41.5M [00:01<00:10, 3.78MB/s]
- 10%|9 | 4.12M/41.5M [00:01<00:08, 4.77MB/s]
- 13%|#3 | 5.41M/41.5M [00:01<00:06, 5.56MB/s]
- 16%|#6 | 6.78M/41.5M [00:02<00:05, 6.22MB/s]
- 20%|#9 | 8.20M/41.5M [00:02<00:05, 6.76MB/s]
- 23%|##3 | 9.67M/41.5M [00:02<00:04, 7.23MB/s]
- 27%|##6 | 11.1M/41.5M [00:02<00:04, 7.56MB/s]
- 30%|### | 12.6M/41.5M [00:02<00:03, 7.76MB/s]
- 34%|###3 | 14.1M/41.5M [00:02<00:03, 7.92MB/s]
- 37%|###7 | 15.6M/41.5M [00:03<00:03, 8.02MB/s]
- 41%|####1 | 17.0M/41.5M [00:03<00:03, 8.10MB/s]
- 45%|####4 | 18.5M/41.5M [00:03<00:02, 8.16MB/s]
- 48%|####8 | 20.0M/41.5M [00:03<00:02, 8.20MB/s]
- 52%|#####1 | 21.4M/41.5M [00:03<00:02, 8.22MB/s]
- 55%|#####5 | 22.9M/41.5M [00:04<00:02, 8.24MB/s]
- 59%|#####8 | 24.4M/41.5M [00:04<00:02, 8.26MB/s]
- 62%|######2 | 25.9M/41.5M [00:04<00:01, 8.27MB/s]
- 66%|######5 | 27.3M/41.5M [00:04<00:01, 8.28MB/s]
- 69%|######9 | 28.8M/41.5M [00:04<00:01, 8.55MB/s]
- 73%|#######2 | 30.2M/41.5M [00:04<00:01, 9.78MB/s]
- 75%|#######5 | 31.2M/41.5M [00:05<00:01, 9.52MB/s]
- 78%|#######7 | 32.2M/41.5M [00:05<00:01, 8.11MB/s]
- 80%|######## | 33.2M/41.5M [00:05<00:01, 8.43MB/s]
- 84%|########3 | 34.7M/41.5M [00:05<00:00, 8.37MB/s]
- 87%|########7 | 36.1M/41.5M [00:05<00:00, 9.76MB/s]
- 89%|########9 | 37.1M/41.5M [00:05<00:00, 8.71MB/s]
- 92%|#########1| 38.0M/41.5M [00:05<00:00, 7.49MB/s]
- 94%|#########4| 39.1M/41.5M [00:06<00:00, 8.06MB/s]
- 98%|#########7| 40.5M/41.5M [00:06<00:00, 9.60MB/s]
-100%|##########| 41.5M/41.5M [00:06<00:00, 6.86MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:31, 96.3kB/s]
+ 0%| | 48.0k/41.5M [00:00<04:49, 150kB/s]
+ 0%| | 88.0k/41.5M [00:00<03:52, 186kB/s]
+ 0%| | 128k/41.5M [00:00<03:35, 201kB/s]
+ 0%| | 184k/41.5M [00:00<03:00, 240kB/s]
+ 1%| | 232k/41.5M [00:01<02:55, 247kB/s]
+ 1%| | 288k/41.5M [00:01<02:42, 266kB/s]
+ 1%| | 344k/41.5M [00:01<02:35, 278kB/s]
+ 1%| | 408k/41.5M [00:01<02:22, 301kB/s]
+ 1%|1 | 472k/41.5M [00:01<02:16, 316kB/s]
+ 1%|1 | 536k/41.5M [00:02<02:11, 326kB/s]
+ 1%|1 | 608k/41.5M [00:02<02:04, 345kB/s]
+ 2%|1 | 688k/41.5M [00:02<01:55, 370kB/s]
+ 2%|1 | 760k/41.5M [00:02<01:54, 373kB/s]
+ 2%|1 | 840k/41.5M [00:02<01:49, 389kB/s]
+ 2%|2 | 928k/41.5M [00:02<01:42, 414kB/s]
+ 2%|2 | 0.99M/41.5M [00:03<01:37, 435kB/s]
+ 3%|2 | 1.09M/41.5M [00:03<01:31, 465kB/s]
+ 3%|2 | 1.19M/41.5M [00:03<01:24, 498kB/s]
+ 3%|3 | 1.29M/41.5M [00:03<01:20, 521kB/s]
+ 3%|3 | 1.39M/41.5M [00:03<01:18, 537kB/s]
+ 4%|3 | 1.50M/41.5M [00:04<01:14, 559kB/s]
+ 4%|3 | 1.61M/41.5M [00:04<01:12, 576kB/s]
+ 4%|4 | 1.73M/41.5M [00:04<01:08, 605kB/s]
+ 4%|4 | 1.85M/41.5M [00:04<01:04, 640kB/s]
+ 5%|4 | 1.98M/41.5M [00:04<01:01, 678kB/s]
+ 5%|5 | 2.12M/41.5M [00:05<00:58, 705kB/s]
+ 5%|5 | 2.26M/41.5M [00:05<00:55, 735kB/s]
+ 6%|5 | 2.41M/41.5M [00:05<00:50, 818kB/s]
+ 6%|6 | 2.56M/41.5M [00:05<00:48, 845kB/s]
+ 7%|6 | 2.73M/41.5M [00:05<00:46, 875kB/s]
+ 7%|6 | 2.90M/41.5M [00:05<00:43, 932kB/s]
+ 7%|7 | 3.09M/41.5M [00:06<00:45, 891kB/s]
+ 8%|7 | 3.27M/41.5M [00:06<00:40, 995kB/s]
+ 8%|8 | 3.48M/41.5M [00:06<00:38, 1.04MB/s]
+ 9%|8 | 3.68M/41.5M [00:06<00:33, 1.18MB/s]
+ 9%|9 | 3.88M/41.5M [00:06<00:31, 1.26MB/s]
+ 10%|9 | 4.01M/41.5M [00:06<00:33, 1.17MB/s]
+ 10%|9 | 4.12M/41.5M [00:07<00:39, 992kB/s]
+ 10%|# | 4.34M/41.5M [00:07<00:33, 1.15MB/s]
+ 11%|#1 | 4.59M/41.5M [00:07<00:31, 1.22MB/s]
+ 12%|#1 | 4.84M/41.5M [00:07<00:27, 1.42MB/s]
+ 12%|#2 | 5.09M/41.5M [00:07<00:24, 1.55MB/s]
+ 13%|#2 | 5.25M/41.5M [00:07<00:26, 1.43MB/s]
+ 13%|#2 | 5.39M/41.5M [00:07<00:29, 1.30MB/s]
+ 14%|#3 | 5.68M/41.5M [00:08<00:23, 1.59MB/s]
+ 14%|#4 | 5.86M/41.5M [00:08<00:22, 1.65MB/s]
+ 15%|#4 | 6.02M/41.5M [00:08<00:27, 1.36MB/s]
+ 15%|#5 | 6.32M/41.5M [00:08<00:23, 1.58MB/s]
+ 16%|#6 | 6.66M/41.5M [00:08<00:19, 1.90MB/s]
+ 17%|#6 | 6.85M/41.5M [00:08<00:18, 1.93MB/s]
+ 17%|#6 | 7.05M/41.5M [00:08<00:22, 1.64MB/s]
+ 18%|#7 | 7.39M/41.5M [00:09<00:18, 1.89MB/s]
+ 19%|#8 | 7.77M/41.5M [00:09<00:15, 2.25MB/s]
+ 20%|#9 | 8.17M/41.5M [00:09<00:14, 2.48MB/s]
+ 20%|## | 8.42M/41.5M [00:09<00:15, 2.30MB/s]
+ 21%|## | 8.65M/41.5M [00:09<00:16, 2.11MB/s]
+ 22%|##1 | 9.10M/41.5M [00:09<00:13, 2.59MB/s]
+ 23%|##3 | 9.58M/41.5M [00:09<00:11, 2.91MB/s]
+ 24%|##3 | 9.87M/41.5M [00:10<00:12, 2.70MB/s]
+ 24%|##4 | 10.1M/41.5M [00:10<00:13, 2.48MB/s]
+ 26%|##5 | 10.7M/41.5M [00:10<00:10, 3.10MB/s]
+ 27%|##7 | 11.2M/41.5M [00:10<00:08, 3.63MB/s]
+ 28%|##7 | 11.6M/41.5M [00:10<00:09, 3.26MB/s]
+ 29%|##8 | 11.9M/41.5M [00:10<00:10, 2.84MB/s]
+ 30%|### | 12.5M/41.5M [00:10<00:08, 3.39MB/s]
+ 32%|###1 | 13.1M/41.5M [00:10<00:07, 3.85MB/s]
+ 33%|###3 | 13.8M/41.5M [00:11<00:06, 4.23MB/s]
+ 34%|###4 | 14.2M/41.5M [00:11<00:07, 3.88MB/s]
+ 35%|###5 | 14.6M/41.5M [00:11<00:08, 3.25MB/s]
+ 37%|###6 | 15.3M/41.5M [00:11<00:07, 3.87MB/s]
+ 39%|###8 | 16.1M/41.5M [00:11<00:05, 4.82MB/s]
+ 40%|###9 | 16.6M/41.5M [00:11<00:05, 4.42MB/s]
+ 41%|####1 | 17.0M/41.5M [00:11<00:06, 3.75MB/s]
+ 43%|####2 | 17.8M/41.5M [00:12<00:05, 4.45MB/s]
+ 45%|####5 | 18.8M/41.5M [00:12<00:04, 5.62MB/s]
+ 47%|####6 | 19.3M/41.5M [00:12<00:04, 5.15MB/s]
+ 48%|####7 | 19.9M/41.5M [00:12<00:05, 4.41MB/s]
+ 50%|##### | 20.8M/41.5M [00:12<00:04, 5.23MB/s]
+ 53%|#####2 | 21.9M/41.5M [00:12<00:03, 6.58MB/s]
+ 54%|#####4 | 22.5M/41.5M [00:12<00:03, 6.08MB/s]
+ 56%|#####5 | 23.2M/41.5M [00:13<00:03, 5.24MB/s]
+ 58%|#####8 | 24.2M/41.5M [00:13<00:02, 6.12MB/s]
+ 61%|######1 | 25.4M/41.5M [00:13<00:02, 6.46MB/s]
+ 64%|######4 | 26.8M/41.5M [00:13<00:01, 7.95MB/s]
+ 66%|######6 | 27.6M/41.5M [00:13<00:01, 7.34MB/s]
+ 68%|######8 | 28.3M/41.5M [00:13<00:02, 6.34MB/s]
+ 71%|#######1 | 29.6M/41.5M [00:13<00:01, 7.37MB/s]
+ 75%|#######4 | 31.0M/41.5M [00:14<00:01, 8.91MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:14<00:01, 8.41MB/s]
+ 79%|#######9 | 32.8M/41.5M [00:14<00:01, 7.12MB/s]
+ 82%|########1 | 34.0M/41.5M [00:14<00:00, 8.22MB/s]
+ 85%|########5 | 35.4M/41.5M [00:14<00:00, 9.85MB/s]
+ 88%|########7 | 36.4M/41.5M [00:14<00:00, 8.46MB/s]
+ 90%|######### | 37.3M/41.5M [00:14<00:00, 7.30MB/s]
+ 93%|#########2| 38.4M/41.5M [00:15<00:00, 8.05MB/s]
+ 96%|#########5| 39.8M/41.5M [00:15<00:00, 9.69MB/s]
+ 98%|#########8| 40.8M/41.5M [00:15<00:00, 8.33MB/s]
+100%|##########| 41.5M/41.5M [00:15<00:00, 2.80MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 34e1034e3..2e0f08aa4 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -469,7 +469,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.558 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.977 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 664c0297c..4d96ef48a 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,9 +387,27 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 36%|###5 | 15.9M/44.7M [00:00<00:00, 166MB/s]
- 84%|########4 | 37.7M/44.7M [00:00<00:00, 203MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 207MB/s]
+ 6%|5 | 2.62M/44.7M [00:00<00:01, 26.9MB/s]
+ 12%|#1 | 5.20M/44.7M [00:00<00:02, 14.9MB/s]
+ 17%|#7 | 7.69M/44.7M [00:00<00:02, 18.5MB/s]
+ 22%|##1 | 9.75M/44.7M [00:00<00:02, 17.5MB/s]
+ 26%|##5 | 11.6M/44.7M [00:00<00:02, 14.0MB/s]
+ 31%|### | 13.8M/44.7M [00:00<00:02, 16.0MB/s]
+ 35%|###4 | 15.5M/44.7M [00:01<00:02, 14.1MB/s]
+ 38%|###8 | 17.1M/44.7M [00:01<00:01, 14.7MB/s]
+ 42%|####1 | 18.6M/44.7M [00:01<00:01, 14.3MB/s]
+ 46%|####6 | 20.7M/44.7M [00:01<00:01, 16.2MB/s]
+ 52%|#####1 | 23.0M/44.7M [00:01<00:01, 18.3MB/s]
+ 56%|#####5 | 24.9M/44.7M [00:01<00:01, 17.5MB/s]
+ 60%|#####9 | 26.7M/44.7M [00:01<00:01, 18.0MB/s]
+ 64%|######3 | 28.5M/44.7M [00:01<00:00, 17.8MB/s]
+ 69%|######9 | 30.9M/44.7M [00:01<00:00, 19.8MB/s]
+ 74%|#######4 | 33.1M/44.7M [00:02<00:00, 20.7MB/s]
+ 80%|#######9 | 35.7M/44.7M [00:02<00:00, 22.3MB/s]
+ 85%|########4 | 37.8M/44.7M [00:02<00:00, 22.3MB/s]
+ 90%|########9 | 40.2M/44.7M [00:02<00:00, 22.9MB/s]
+ 95%|#########4| 42.4M/44.7M [00:02<00:00, 22.8MB/s]
+100%|##########| 44.7M/44.7M [00:02<00:00, 18.7MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index dc4e806f8..77e869f00 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,7 +612,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.332 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.780 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index df9d67128..e45e46040 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:30.132</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:34.644</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:09.558</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
-<li><p><strong>01:04.332</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
-<li><p><strong>00:58.774</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:32.201</strong>: <a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></li>
-<li><p><strong>00:24.105</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
-<li><p><strong>00:23.026</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:21.769</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
-<li><p><strong>00:19.896</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:13.875</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
-<li><p><strong>00:02.596</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
+<li><p><strong>01:06.977</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
+<li><p><strong>01:02.780</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
+<li><p><strong>00:57.892</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
+<li><p><strong>00:40.873</strong>: <a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></li>
+<li><p><strong>00:24.682</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
+<li><p><strong>00:22.335</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:21.765</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:21.084</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
+<li><p><strong>00:13.744</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
+<li><p><strong>00:02.511</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 7eadc8e5b..83c02fa28 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -627,7 +627,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0902 16.0877 16.2235 15.9769 0.0801
+ 15.6991 15.6979 15.7898 15.6255 0.0513
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
index 10cd4bc13..d6f8f2047 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,53 +409,47 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|1 | 2.62M/170M [00:00<00:06, 27.1MB/s]
- 3%|3 | 5.21M/170M [00:00<00:06, 25.4MB/s]
- 6%|6 | 10.5M/170M [00:00<00:04, 38.2MB/s]
- 9%|8 | 14.4M/170M [00:00<00:04, 39.3MB/s]
- 11%|# | 18.2M/170M [00:00<00:04, 34.4MB/s]
- 13%|#2 | 21.9M/170M [00:00<00:04, 35.5MB/s]
- 15%|#5 | 25.7M/170M [00:00<00:04, 36.9MB/s]
- 19%|#8 | 31.4M/170M [00:00<00:03, 43.9MB/s]
- 22%|##1 | 36.7M/170M [00:00<00:02, 47.2MB/s]
- 24%|##4 | 41.2M/170M [00:01<00:02, 45.5MB/s]
- 27%|##6 | 45.6M/170M [00:01<00:03, 42.2MB/s]
- 29%|##9 | 49.7M/170M [00:01<00:03, 39.4MB/s]
- 32%|###1 | 53.6M/170M [00:01<00:03, 38.6MB/s]
- 34%|###4 | 58.2M/170M [00:01<00:02, 41.2MB/s]
- 37%|###6 | 62.2M/170M [00:01<00:03, 31.8MB/s]
- 39%|###8 | 66.1M/170M [00:01<00:03, 33.6MB/s]
- 41%|####1 | 69.8M/170M [00:01<00:03, 34.5MB/s]
- 43%|####3 | 73.3M/170M [00:02<00:03, 32.9MB/s]
- 45%|####5 | 76.9M/170M [00:02<00:02, 34.0MB/s]
- 47%|####7 | 80.3M/170M [00:02<00:02, 33.2MB/s]
- 49%|####9 | 83.6M/170M [00:02<00:03, 27.8MB/s]
- 51%|##### | 86.4M/170M [00:02<00:03, 27.0MB/s]
- 52%|#####2 | 89.1M/170M [00:02<00:03, 26.8MB/s]
- 56%|#####5 | 95.0M/170M [00:02<00:02, 35.9MB/s]
- 58%|#####8 | 98.8M/170M [00:02<00:02, 36.9MB/s]
- 60%|###### | 102M/170M [00:03<00:02, 32.1MB/s]
- 62%|######2 | 106M/170M [00:03<00:02, 26.4MB/s]
- 65%|######4 | 110M/170M [00:03<00:02, 31.2MB/s]
- 67%|######6 | 114M/170M [00:03<00:02, 25.9MB/s]
- 69%|######8 | 116M/170M [00:03<00:02, 20.5MB/s]
- 70%|######9 | 119M/170M [00:03<00:02, 21.2MB/s]
- 71%|#######1 | 121M/170M [00:03<00:02, 22.3MB/s]
- 73%|#######2 | 124M/170M [00:04<00:02, 23.6MB/s]
- 75%|#######4 | 127M/170M [00:04<00:01, 25.2MB/s]
- 78%|#######7 | 132M/170M [00:04<00:01, 31.9MB/s]
- 80%|######## | 137M/170M [00:04<00:00, 37.2MB/s]
- 83%|########2 | 140M/170M [00:04<00:01, 29.1MB/s]
- 85%|########4 | 144M/170M [00:04<00:01, 25.9MB/s]
- 86%|########6 | 146M/170M [00:04<00:00, 26.8MB/s]
- 88%|########7 | 149M/170M [00:04<00:00, 26.9MB/s]
- 90%|########9 | 152M/170M [00:05<00:00, 27.6MB/s]
- 92%|#########1| 156M/170M [00:05<00:00, 31.1MB/s]
- 94%|#########3| 159M/170M [00:05<00:00, 31.2MB/s]
- 96%|#########5| 163M/170M [00:05<00:00, 33.4MB/s]
- 98%|#########7| 166M/170M [00:05<00:00, 33.0MB/s]
-100%|#########9| 169M/170M [00:05<00:00, 31.7MB/s]
-100%|##########| 170M/170M [00:05<00:00, 31.7MB/s]
+ 2%|2 | 4.06M/170M [00:00<00:04, 42.6MB/s]
+ 5%|4 | 8.45M/170M [00:00<00:03, 44.5MB/s]
+ 7%|7 | 12.7M/170M [00:00<00:03, 41.8MB/s]
+ 10%|9 | 16.7M/170M [00:00<00:04, 38.4MB/s]
+ 12%|#2 | 20.4M/170M [00:00<00:05, 28.8MB/s]
+ 15%|#4 | 24.8M/170M [00:00<00:04, 33.2MB/s]
+ 17%|#6 | 28.6M/170M [00:00<00:04, 34.7MB/s]
+ 20%|#9 | 33.2M/170M [00:00<00:03, 38.7MB/s]
+ 22%|##1 | 37.2M/170M [00:01<00:03, 37.1MB/s]
+ 24%|##4 | 40.8M/170M [00:01<00:03, 37.4MB/s]
+ 27%|##6 | 45.2M/170M [00:01<00:03, 39.6MB/s]
+ 29%|##8 | 49.1M/170M [00:01<00:03, 39.0MB/s]
+ 32%|###2 | 54.4M/170M [00:01<00:02, 43.5MB/s]
+ 35%|###4 | 58.6M/170M [00:01<00:02, 43.8MB/s]
+ 37%|###7 | 63.5M/170M [00:01<00:02, 45.7MB/s]
+ 40%|#### | 68.1M/170M [00:01<00:02, 46.4MB/s]
+ 43%|####2 | 72.6M/170M [00:01<00:02, 43.2MB/s]
+ 45%|####5 | 76.8M/170M [00:02<00:02, 42.0MB/s]
+ 48%|####8 | 81.5M/170M [00:02<00:02, 44.2MB/s]
+ 51%|##### | 85.8M/170M [00:02<00:02, 35.6MB/s]
+ 53%|#####2 | 89.5M/170M [00:02<00:02, 34.4MB/s]
+ 55%|#####4 | 93.0M/170M [00:02<00:02, 34.9MB/s]
+ 57%|#####7 | 97.4M/170M [00:02<00:02, 37.7MB/s]
+ 60%|###### | 102M/170M [00:02<00:01, 40.4MB/s]
+ 63%|######2 | 107M/170M [00:02<00:01, 43.2MB/s]
+ 65%|######5 | 111M/170M [00:03<00:01, 36.3MB/s]
+ 68%|######7 | 115M/170M [00:03<00:01, 36.7MB/s]
+ 70%|####### | 119M/170M [00:03<00:01, 39.5MB/s]
+ 73%|#######3 | 124M/170M [00:03<00:01, 42.2MB/s]
+ 76%|#######5 | 128M/170M [00:03<00:01, 40.4MB/s]
+ 78%|#######7 | 132M/170M [00:03<00:01, 35.3MB/s]
+ 80%|######## | 136M/170M [00:03<00:01, 33.9MB/s]
+ 82%|########2 | 139M/170M [00:03<00:01, 29.5MB/s]
+ 84%|########3 | 142M/170M [00:04<00:01, 26.7MB/s]
+ 86%|########5 | 145M/170M [00:04<00:00, 27.9MB/s]
+ 88%|########8 | 150M/170M [00:04<00:00, 33.8MB/s]
+ 91%|#########1| 155M/170M [00:04<00:00, 38.6MB/s]
+ 94%|#########3| 159M/170M [00:04<00:00, 37.3MB/s]
+ 96%|#########6| 164M/170M [00:04<00:00, 39.9MB/s]
+ 99%|#########8| 168M/170M [00:04<00:00, 40.6MB/s]
+100%|##########| 170M/170M [00:04<00:00, 37.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -553,7 +547,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.846 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 57.931 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index b2e68fc7a..81e066e63 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 182MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 201MB/s]
</pre></div>
</div>
</div>
@@ -544,7 +544,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3933 90.3727 90.9154 90.2584 0.1033
+ 90.3258 90.2362 93.6856 90.0742 0.3973
</pre></div>
</div>
<div class="admonition note">
@@ -583,7 +583,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.722 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.565 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 5ac427117..eb960708f 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -545,7 +545,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.0126 119.9351 125.6041 119.2173 0.6736
+ 118.4617 118.4777 119.7582 117.4165 0.3981
</pre></div>
</div>
<div class="admonition note">
@@ -573,7 +573,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.798 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.398 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index f2d05f6f4..c32439dba 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -482,7 +482,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.634 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.188 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 387add8e8..f1e275f2f 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,22 +415,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6237/132723 [00:00<00:02, 62363.52KB/s]
- 11%|#1 | 15067/132723 [00:00<00:01, 77614.76KB/s]
- 18%|#7 | 23815/132723 [00:00<00:01, 82114.21KB/s]
- 25%|##4 | 32633/132723 [00:00<00:01, 84507.19KB/s]
- 31%|###1 | 41418/132723 [00:00<00:01, 85709.94KB/s]
- 38%|###7 | 50270/132723 [00:00<00:00, 86663.93KB/s]
- 45%|####4 | 59145/132723 [00:00<00:00, 87341.75KB/s]
- 51%|#####1 | 67960/132723 [00:00<00:00, 87596.21KB/s]
- 58%|#####7 | 76843/132723 [00:00<00:00, 87979.09KB/s]
- 65%|######4 | 85641/132723 [00:01<00:00, 87802.14KB/s]
- 71%|#######1 | 94431/132723 [00:01<00:00, 87829.19KB/s]
- 78%|#######7 | 103229/132723 [00:01<00:00, 87869.57KB/s]
- 84%|########4 | 112058/132723 [00:01<00:00, 87993.88KB/s]
- 91%|#########1| 120858/132723 [00:01<00:00, 81135.56KB/s]
- 98%|#########7| 129784/132723 [00:01<00:00, 83440.76KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 84857.48KB/s]
+ 2%|2 | 3237/132723 [00:00<00:04, 31959.25KB/s]
+ 7%|6 | 9111/132723 [00:00<00:02, 47627.21KB/s]
+ 13%|#3 | 17710/132723 [00:00<00:01, 65091.50KB/s]
+ 20%|#9 | 26382/132723 [00:00<00:01, 73612.50KB/s]
+ 26%|##6 | 35097/132723 [00:00<00:01, 78487.11KB/s]
+ 33%|###3 | 43861/132723 [00:00<00:01, 81595.46KB/s]
+ 39%|###9 | 52393/132723 [00:00<00:00, 82805.64KB/s]
+ 46%|####6 | 61131/132723 [00:00<00:00, 84259.84KB/s]
+ 53%|#####2 | 69817/132723 [00:00<00:00, 85065.63KB/s]
+ 59%|#####9 | 78546/132723 [00:01<00:00, 85750.22KB/s]
+ 66%|######5 | 87278/132723 [00:01<00:00, 86227.50KB/s]
+ 72%|#######2 | 96002/132723 [00:01<00:00, 86534.30KB/s]
+ 79%|#######8 | 104761/132723 [00:01<00:00, 86845.06KB/s]
+ 85%|########5 | 113446/132723 [00:01<00:00, 85827.59KB/s]
+ 92%|#########1| 122075/132723 [00:01<00:00, 85963.69KB/s]
+ 99%|#########8| 130841/132723 [00:01<00:00, 86467.68KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 81470.34KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -475,7 +476,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.786 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 16.018 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index c012615f0..746a4f439 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:49.110</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:24.913</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:02.846</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
-<li><p><strong>02:20.786</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
-<li><p><strong>01:58.798</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
-<li><p><strong>01:26.634</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
-<li><p><strong>01:07.722</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
-<li><p><strong>00:29.348</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
-<li><p><strong>00:22.765</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
-<li><p><strong>00:00.210</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
+<li><p><strong>02:57.931</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
+<li><p><strong>02:16.018</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
+<li><p><strong>01:58.398</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
+<li><p><strong>01:15.188</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
+<li><p><strong>01:05.565</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
+<li><p><strong>00:29.269</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
+<li><p><strong>00:22.346</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
+<li><p><strong>00:00.197</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 990a9af57..35e564f7b 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -590,7 +590,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipd61adcdc-323e-4f61-bf3f-05c00fda9368 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip91778866-356d-48f0-83b8-4dc691e0c584 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 0a72d920f..9a628708d 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.074</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:39.739</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:37.248</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
-<li><p><strong>00:02.465</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
-<li><p><strong>00:01.145</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
-<li><p><strong>00:00.216</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:36.044</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
+<li><p><strong>00:02.410</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
+<li><p><strong>00:01.086</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
+<li><p><strong>00:00.199</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index cae6cef35..9e3ed3f7b 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6867us [6867us] (45.97%; 45.97%)
-FoldScaleAxis: 8071us [7us] (54.03%; 54.03%)
- FoldConstant: 8064us [1594us] (53.98%; 99.91%)
- InferType: 6470us [6470us] (43.31%; 80.23%)
+InferType: 7570us [7570us] (47.66%; 47.66%)
+FoldScaleAxis: 8313us [7us] (52.34%; 52.34%)
+ FoldConstant: 8306us [1697us] (52.30%; 99.92%)
+ InferType: 6609us [6609us] (41.61%; 79.57%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6511us [6511us] (44.95%; 44.95%)
-FoldScaleAxis: 7974us [6us] (55.05%; 55.05%)
- FoldConstant: 7968us [1625us] (55.01%; 99.93%)
- InferType: 6343us [6343us] (43.79%; 79.60%)
+InferType: 6582us [6582us] (44.59%; 44.59%)
+FoldScaleAxis: 8179us [5us] (55.41%; 55.41%)
+ FoldConstant: 8174us [1666us] (55.38%; 99.94%)
+ InferType: 6509us [6509us] (44.09%; 79.62%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index f45821d8d..a07a6e0a6 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.152333 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.144555 ms
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index ecd24af5c..2119c363e 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.564221 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.206228 ms
</pre></div>
</div>
</div>
diff --git a/docs/how_to/optimize_operators/opt_gemm.html b/docs/how_to/optimize_operators/opt_gemm.html
index da4238f54..def5afc8d 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019254
-Baseline: 3.429668
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018107
+Baseline: 3.514277
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -494,7 +494,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.305701
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.304224
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -563,7 +563,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336352
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335820
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -626,7 +626,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118276
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120454
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -711,7 +711,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110659
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110737
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111297
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111545
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -891,7 +891,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145612
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144740
</pre></div>
</div>
<p>Here is the generated IR after parallelization.</p>
diff --git a/docs/how_to/optimize_operators/sg_execution_times.html b/docs/how_to/optimize_operators/sg_execution_times.html
index 347e6aea7..cab7b3dd6 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.433</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.365</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.652</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
-<li><p><strong>00:01.494</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
-<li><p><strong>00:01.287</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
+<li><p><strong>00:32.708</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
+<li><p><strong>00:01.429</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
+<li><p><strong>00:01.228</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index fc139e73b..1f9334cbf 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:16.528</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:12.774</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:33.953</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
-<li><p><strong>01:21.230</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
-<li><p><strong>00:43.625</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
-<li><p><strong>00:20.075</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
-<li><p><strong>00:08.900</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
-<li><p><strong>00:08.745</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
+<li><p><strong>02:35.151</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
+<li><p><strong>01:20.213</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
+<li><p><strong>00:42.864</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
+<li><p><strong>00:17.515</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
+<li><p><strong>00:08.537</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
+<li><p><strong>00:08.494</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 987d4aae1..72b80b743 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -470,12 +470,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -483,470 +483,618 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
+ for (rc.outer.outer: int32, 0, 8) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_4: int32 = (rc.outer.outer*3136)
+ let cse_var_3: int32 = (ry.outer.outer*7)
+ let cse_var_2: int32 = (rc.outer.outer*576)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 49), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 98), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 147), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 147), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 147), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 196), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 245), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 245), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 245), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 294), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 294), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 294), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 343)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 343), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 343), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 343), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 392), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 441)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 335)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 490), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 490), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 490), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 539)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 539), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 539), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 539), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 588), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 637), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 637), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 637), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 686), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 686), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 686), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 735)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 735), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 735), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 735), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 833)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 833), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 833), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 678)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 931)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 931), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 931), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 931), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 980), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1029)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1029), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1029), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1029), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1078), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1078), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1078), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1127)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1127), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1127), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1127), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1225)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1225), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1225), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1225), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 1274), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1274), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1323)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1021)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1372), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1421)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1421), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1421), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1421), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1470), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1470), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1470), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1519)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1519), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1519), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1519), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1617)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1617), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1617), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1617), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1666), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1666), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1666), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1715)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 1715), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1715), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1813)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1813), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1813), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1813), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1862), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1862), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1862), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1911)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1911), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1911), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1911), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2009)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2009), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2009), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2009), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2058), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2058), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2058), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2107)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2107), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2107), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2107), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 2156), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2156), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2205)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1707)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2254), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2254), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2254), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2303)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2303), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2303), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2303), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2352), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2352), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2401)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2401), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2401), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2401), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2450), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2450), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2450), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2499)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2499), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2499), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2499), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2548), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2548), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2548), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2597)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 2597), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2597), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2646)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2050)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2695)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2695), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2695), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2695), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2744), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2744), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2744), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2793)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2793), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2793), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2793), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2842)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2842), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2842), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2842), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2891)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2891), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2891), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2891), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2940), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2940), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2940), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 2989)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 2989), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 2989), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2989), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3038)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 3038), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3038), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3087)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2393)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3136), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3136), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3185)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3185), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3185), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3185), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3234)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3234), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3234), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3234), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3283)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3283), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3283), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3283), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3332), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3332), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3332), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3381)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3381), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3381), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3381), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3430)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3430), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3430), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3430), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3479)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 3479), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3479), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3577)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3577), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3577), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3577), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3626)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3626), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3626), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3626), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3675)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3675), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3675), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3675), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3724), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3724), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3724), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3773)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3773), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3773), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3773), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3822)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3822), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3822), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3822), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3871)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 3871), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 3871), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3871), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 3920), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3920), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 3969)] = @tir.if_then_else((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 3079)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 4018)] = @tir.if_then_else(((((floordiv(floormod((threadIdx.x_1 + 4018), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 4018), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[(threadIdx.x_2*12)] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 2)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 3)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 9)]
+ kernel.shared_1[((threadIdx.x_2*12) + 4)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 10)]
+ kernel.shared_1[((threadIdx.x_2*12) + 5)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 11)]
+ kernel.shared_1[((threadIdx.x_2*12) + 6)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 18)]
+ kernel.shared_1[((threadIdx.x_2*12) + 7)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 19)]
+ kernel.shared_1[((threadIdx.x_2*12) + 8)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 20)]
+ kernel.shared_1[((threadIdx.x_2*12) + 9)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 27)]
+ kernel.shared_1[((threadIdx.x_2*12) + 10)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 28)]
+ kernel.shared_1[((threadIdx.x_2*12) + 11)] = kernel[((((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + cse_var_2) + (floormod(threadIdx.x_2, 16)*36)) + cse_var_1) + 29)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ kernel.shared_1[((threadIdx.x_2*12) + 588)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 4), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 589)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 4), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 590)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 4), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 591)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 5), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 592)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 5), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 593)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 5), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 594)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 6), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 595)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 6), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 596)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 6), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 597)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 7), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 598)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 7), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 599)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 7), 64)*9)) + cse_var_1) + 2)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 30), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*12) + 1176)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 8), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1177)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 8), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1178)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 8), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1179)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 9), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1180)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 9), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1181)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 9), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1182)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 10), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1183)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 10), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1184)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 10), 64)*9)) + cse_var_1) + 2)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1185)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 11), 64)*9)) + cse_var_1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1186)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 11), 64)*9)) + cse_var_1) + 1)]
+ kernel.shared_1[((threadIdx.x_2*12) + 1187)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 16)*4608)) + cse_var_2) + (floormod(((threadIdx.x_2*4) + 11), 64)*9)) + cse_var_1) + 2)]
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ let cse_var_5: int32 = (rc.outer.inner*48)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_5]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 192)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 195)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 198)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 201)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 204)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 207)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 210)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 213)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 216)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 219)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 222)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 234)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 237)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 384)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 387)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 390)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 393)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 396)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 399)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 402)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 405)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 408)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 411)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 414)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 417)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 420)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 423)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 426)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 429)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 597)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 600)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 606)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 609)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 612)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 615)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 618)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 621)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 768)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 771)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 774)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 777)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 780)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 783)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 786)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 789)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 792)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 795)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 798)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 801)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 804)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 807)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 810)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 813)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 960)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 963)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 966)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 969)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 972)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 975)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 978)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 981)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 984)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 987)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 990)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 993)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 996)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 999)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 1002)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 1005)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 1152)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 1155)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 1158)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 1161)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 1164)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 1167)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 1170)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 1173)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 1176)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 1179)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 1182)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 1185)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 1188)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 1191)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 1194)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 1197)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 1344)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 1347)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 1350)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 1353)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 1356)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 1359)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 1362)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 1365)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(cse_var_5 + 1368)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(cse_var_5 + 1371)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(cse_var_5 + 1374)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(cse_var_5 + 1377)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(cse_var_5 + 1380)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(cse_var_5 + 1383)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(cse_var_5 + 1386)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(cse_var_5 + 1389)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 193)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 196)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 199)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 202)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 205)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 208)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 211)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 214)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 217)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 220)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 223)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 226)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 229)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 232)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 235)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 238)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 385)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 388)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 391)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 394)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 397)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 400)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 403)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 406)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 409)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 412)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 415)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 418)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 421)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 424)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 427)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 430)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 580)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 583)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 589)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 592)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 595)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 598)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 601)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 604)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 607)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 610)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 613)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 616)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 619)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 622)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 769)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 772)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 775)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 778)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 781)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 784)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 787)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 790)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 793)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 796)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 799)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 802)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 805)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 808)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 811)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 814)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 961)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 964)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 967)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 970)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 973)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 976)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 979)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 982)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 985)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 988)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 991)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 994)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 997)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 1000)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 1003)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 1006)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1153)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 1156)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 1159)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 1162)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 1165)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 1168)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 1171)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 1174)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 1177)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 1180)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 1183)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 1186)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 1189)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 1192)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 1195)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 1198)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1345)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 1348)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 1351)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 1354)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 1357)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 1360)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 1363)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 1366)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[(cse_var_5 + 1369)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(cse_var_5 + 1372)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[(cse_var_5 + 1375)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[(cse_var_5 + 1378)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[(cse_var_5 + 1381)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[(cse_var_5 + 1384)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[(cse_var_5 + 1387)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[(cse_var_5 + 1390)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 194)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 197)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 200)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 203)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 206)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 209)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 212)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 215)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 218)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 221)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 224)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 227)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 230)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 233)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 236)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 239)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 386)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 389)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 392)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 395)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 398)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 401)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 404)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 407)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 410)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 413)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 416)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 419)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 422)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 425)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 428)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 431)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 578)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 581)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 587)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 590)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 596)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 599)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 602)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 605)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 608)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 611)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 614)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 617)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 620)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 623)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 770)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 773)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 776)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 779)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 782)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 785)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 788)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 791)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 794)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 797)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 800)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 803)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 806)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 809)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 812)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 815)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 962)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 965)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 968)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 971)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 974)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 977)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 980)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 983)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 986)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 989)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 992)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 995)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 998)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 1001)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 1004)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 1007)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 1154)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 1157)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 1160)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 1163)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 1166)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 1169)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 1172)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 1175)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 1178)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 1181)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 1184)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 1187)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 1190)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 1193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 1196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 1199)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 1346)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 1349)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 1352)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 1355)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 1358)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 1361)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 1364)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 1367)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[(cse_var_5 + 1370)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(cse_var_5 + 1373)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[(cse_var_5 + 1376)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[(cse_var_5 + 1379)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[(cse_var_5 + 1382)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[(cse_var_5 + 1385)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[(cse_var_5 + 1388)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*1008) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[(cse_var_5 + 1391)]))
}
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 208), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 224), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 272), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 304), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 352), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 368), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 400), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 416), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 464), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 496), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 544), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 560), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 592), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 608), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 656), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 688), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 736), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 752), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 8) {
+ compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
}
}
}
@@ -984,7 +1132,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.348 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.305 ms
</pre></div>
</div>
</div>
@@ -1015,18 +1163,18 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
@@ -1036,14 +1184,14 @@ s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nc
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1061,16 +1209,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=12)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1088,10 +1236,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1100,418 +1248,523 @@ extern "C" __global__ void __launch_bounds__(64) default_function_kern
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 49) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 98) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 147) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 245) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 294) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 343) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 441)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 335)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 490) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 539) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 637) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 686) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 735)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 735) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 833)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 833) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 678)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 931)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 931) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1029)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1029) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1078) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1127)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1127) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1225)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1225) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1274) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1323)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1021)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1421)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1421) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1470) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1519)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1519) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1617)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1617) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1666) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1715)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1715) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1813)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1813) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1862) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1911)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1911) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2009)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2009) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2058) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2107)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2107) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2205)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1707)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2254) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2303)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2303) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2401)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2401) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2450) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2499)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2499) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2597)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2597) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2646)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2050)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2695)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2695) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2793)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2793) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2842)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2842) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2891)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2891) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2989)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2989) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3038)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3038) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3087)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3185)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3185) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3234)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3234) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3283)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3283) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3381)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3381) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3430)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3430) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3479)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3479) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3577)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3577) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3626)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3626) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3675)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3675) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3773)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3773) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3822)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3822) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3871)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3871) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3969)] = ((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 3079)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 14) {
+ pad_temp_shared[(((int)threadIdx.x) + 4018)] = ((((((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 4018) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[(((int)threadIdx.x) * 12)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 2)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 3)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 9)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 4)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 10)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 5)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 11)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 6)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 18)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 7)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 19)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 8)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 20)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 9)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 27)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 10)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 28)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 11)] = kernel[((((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) & 15) * 36)) + (ry_outer_outer * 3)) + 29)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 588)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 4) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 589)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 4) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 590)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 4) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 591)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 5) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 592)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 5) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 593)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 5) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 594)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 6) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 595)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 6) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 596)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 6) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 597)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 7) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 598)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 7) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 599)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 7) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ if (((int)threadIdx.x) < 30) {
+ kernel_shared[((((int)threadIdx.x) * 12) + 1176)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 8) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1177)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 8) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1178)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 8) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1179)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 9) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1180)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 9) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1181)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 9) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1182)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 10) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1183)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 10) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1184)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 10) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1185)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 11) & 63) * 9)) + (ry_outer_outer * 3))];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1186)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 11) & 63) * 9)) + (ry_outer_outer * 3)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 12) + 1187)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) * 4) + 11) & 63) * 9)) + (ry_outer_outer * 3)) + 2)];
}
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 195)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 198)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 201)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 204)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 207)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 210)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 213)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 216)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 219)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 222)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 234)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 237)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 384)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 387)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 390)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 393)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 396)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 399)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 402)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 405)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 408)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 411)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 414)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 417)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 420)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 423)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 426)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 429)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 597)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 600)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 606)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 609)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 612)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 615)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 618)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 621)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 768)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 771)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 774)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 777)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 780)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 783)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 786)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 789)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 792)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 795)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 798)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 801)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 804)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 807)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 810)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 813)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 960)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 963)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 966)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 969)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 972)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 975)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 978)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 981)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 984)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 987)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 990)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 993)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 996)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 999)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 1002)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 1005)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 1152)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 1155)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 1158)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 1161)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 1164)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 1167)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 1170)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 1173)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 1176)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 1179)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 1182)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 1185)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 1188)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 1191)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 1194)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 1197)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 48) + 1344)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((rc_outer_inner * 48) + 1347)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((rc_outer_inner * 48) + 1350)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((rc_outer_inner * 48) + 1353)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((rc_outer_inner * 48) + 1356)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((rc_outer_inner * 48) + 1359)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((rc_outer_inner * 48) + 1362)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((rc_outer_inner * 48) + 1365)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((rc_outer_inner * 48) + 1368)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((rc_outer_inner * 48) + 1371)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((rc_outer_inner * 48) + 1374)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((rc_outer_inner * 48) + 1377)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((rc_outer_inner * 48) + 1380)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((rc_outer_inner * 48) + 1383)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((rc_outer_inner * 48) + 1386)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((rc_outer_inner * 48) + 1389)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 193)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 196)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 199)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 202)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 205)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 208)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 211)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 214)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 217)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 220)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 223)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 226)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 229)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 232)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 235)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 238)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 385)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 388)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 391)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 394)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 397)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 400)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 403)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 406)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 409)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 412)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 415)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 418)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 421)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 424)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 427)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 430)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 580)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 583)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 589)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 592)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 595)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 598)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 601)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 604)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 607)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 610)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 613)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 616)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 619)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 622)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 769)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 772)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 775)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 778)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 781)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 784)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 787)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 790)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 793)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 796)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 799)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 802)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 805)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 808)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 811)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 814)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 961)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 964)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 967)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 970)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 973)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 976)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 979)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 982)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 985)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 988)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 991)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 994)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 997)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 1000)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 1003)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 1006)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 1153)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 1156)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 1159)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 1162)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 1165)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 1168)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 1171)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 1174)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 1177)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 1180)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 1183)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 1186)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 1189)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 1192)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 1195)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 1198)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 48) + 1345)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((rc_outer_inner * 48) + 1348)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((rc_outer_inner * 48) + 1351)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((rc_outer_inner * 48) + 1354)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((rc_outer_inner * 48) + 1357)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((rc_outer_inner * 48) + 1360)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((rc_outer_inner * 48) + 1363)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((rc_outer_inner * 48) + 1366)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[((rc_outer_inner * 48) + 1369)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((rc_outer_inner * 48) + 1372)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[((rc_outer_inner * 48) + 1375)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[((rc_outer_inner * 48) + 1378)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[((rc_outer_inner * 48) + 1381)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[((rc_outer_inner * 48) + 1384)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[((rc_outer_inner * 48) + 1387)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[((rc_outer_inner * 48) + 1390)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 194)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 197)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 200)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 203)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 206)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 209)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 212)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 215)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 218)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 221)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 224)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 227)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 230)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 233)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 236)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 239)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 386)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 389)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 392)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 395)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 398)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 401)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 404)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 407)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 410)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 413)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 416)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 419)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 422)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 425)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 428)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 431)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 578)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 581)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 587)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 590)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 596)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 599)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 602)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 605)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 608)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 611)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 614)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 617)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 620)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 623)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 770)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 773)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 776)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 779)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 782)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 785)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 788)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 791)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 794)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 797)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 800)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 803)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 806)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 809)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 812)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 815)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 962)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 965)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 968)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 971)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 974)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 977)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 980)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 983)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 986)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 989)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 992)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 995)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 998)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 1001)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 1004)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 1007)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 1154)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 1157)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 1160)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 1163)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 1166)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 1169)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 1172)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 1175)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 1178)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 1181)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 1184)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 1187)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 1190)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 1193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 1196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 1199)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 48) + 1346)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((rc_outer_inner * 48) + 1349)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((rc_outer_inner * 48) + 1352)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((rc_outer_inner * 48) + 1355)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((rc_outer_inner * 48) + 1358)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((rc_outer_inner * 48) + 1361)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((rc_outer_inner * 48) + 1364)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((rc_outer_inner * 48) + 1367)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[((rc_outer_inner * 48) + 1370)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((rc_outer_inner * 48) + 1373)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[((rc_outer_inner * 48) + 1376)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[((rc_outer_inner * 48) + 1379)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[((rc_outer_inner * 48) + 1382)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[((rc_outer_inner * 48) + 1385)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[((rc_outer_inner * 48) + 1388)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 1008) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[((rc_outer_inner * 48) + 1391)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1549,7 +1802,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 33.953 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.151 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index ffec89340..d982393e6 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -878,7 +878,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.4903 9.4911 9.4979 9.4817 0.0066
+ 9.7428 9.7631 9.7740 9.6913 0.0367
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 658e3cc38..a69db39f1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -897,7 +897,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 761.6862 761.8040 761.9038 761.3507 0.2407
+ 749.8626 750.5058 751.4467 747.6353 1.6211
</pre></div>
</div>
</div>
@@ -919,7 +919,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.230 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.213 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index be3dafa08..8b8b5c597 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,78 +600,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 64) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- let cse_var_14: int32 = (cse_var_18 + 6)
- let cse_var_13: int32 = (cse_var_18 + 5)
- let cse_var_12: int32 = (cse_var_18 + 4)
- let cse_var_11: int32 = (cse_var_18 + 3)
- let cse_var_10: int32 = (cse_var_18 + 2)
- let cse_var_9: int32 = (cse_var_18 + 15)
- let cse_var_8: int32 = (cse_var_18 + 14)
- let cse_var_7: int32 = (cse_var_18 + 13)
- let cse_var_6: int32 = (cse_var_18 + 12)
- let cse_var_5: int32 = (cse_var_18 + 11)
- let cse_var_4: int32 = (cse_var_18 + 10)
- let cse_var_3: int32 = (cse_var_18 + 1)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ if let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_4: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_4]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_4] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_5: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_5, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_5, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -710,7 +662,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.861 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.474 ms
</pre></div>
</div>
<div class="admonition note">
diff --git a/docs/how_to/tune_with_autotvm/sg_execution_times.html b/docs/how_to/tune_with_autotvm/sg_execution_times.html
index 73ffab73a..42c0ee751 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.994</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.137</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.072</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.239</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.229</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.229</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
-<li><p><strong>00:00.224</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:43.278</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.228</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
+<li><p><strong>00:00.213</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.211</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:00.209</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index eac67c52d..75fbceb88 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 112.37/112.37 result: MeasureResult(costs=(0.002060116727272727,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8840768337249756, timestamp=1654838616.8286886) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 6 GFLOPS: 103.31/103.31 result: MeasureResult(costs=(0.0022409267291666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.614325761795044, timestamp=1654841523.1741066) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/112.37 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/103.31 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f13b4e4dfa2
+ 12: 0x00007fccb28c4fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 144.09/144.09 result: MeasureResult(costs=(0.00160667445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.433812141418457, timestamp=1654838643.375321) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 143.90/143.90 result: MeasureResult(costs=(0.00160881471,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4116015434265137, timestamp=1654841549.5921435) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.001996
+Time cost of this operator: 0.001997
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 0d28bcf82..4396a8025 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -556,10 +556,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.2 98.767 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.946 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.915 0.287 (1, 1, 10, 10, 3) 1 1
-Total_time - 319.136 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.8 98.741 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.967 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.928 0.292 (1, 1, 10, 10, 3) 1 1
+Total_time - 317.801 - - - -
</pre></div>
</div>
</div>
@@ -611,10 +611,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 328.3 98.778 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.134 0.943 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.927 0.279 (1, 1, 10, 10, 3) 1 1
-Total_time - 332.361 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 227.9 98.789 (1, 1, 10, 10, 6) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.973 0.855 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.821 0.356 (1, 3, 10, 10, 1) 1 1
+Total_time - 230.694 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index e86d02dfb..2d22e57dd 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -552,8 +552,8 @@ objects to other stuff? We can display some examples from our datasets using <co
</div>
<img alt="../../_images/sphx_glr_micro_train_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_micro_train_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpaqr8poau/images/target contains 8144 images
-/tmp/tmpaqr8poau/images/random contains 5000 images
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpzle21gp8/images/target contains 8144 images
+/tmp/tmpzle21gp8/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -666,11 +666,11 @@ the time on our validation set).</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 54s - loss: 0.2182 - accuracy: 0.9275 - val_loss: 0.1462 - val_accuracy: 0.9558
+328/328 - 54s - loss: 0.2550 - accuracy: 0.9161 - val_loss: 0.1391 - val_accuracy: 0.9554
Epoch 2/3
-328/328 - 52s - loss: 0.0988 - accuracy: 0.9627 - val_loss: 0.1110 - val_accuracy: 0.9615
+328/328 - 52s - loss: 0.0980 - accuracy: 0.9617 - val_loss: 0.1138 - val_accuracy: 0.9634
Epoch 3/3
-328/328 - 52s - loss: 0.0669 - accuracy: 0.9751 - val_loss: 0.1186 - val_accuracy: 0.9619
+328/328 - 52s - loss: 0.0696 - accuracy: 0.9740 - val_loss: 0.1179 - val_accuracy: 0.9641
</pre></div>
</div>
</div>
@@ -959,7 +959,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 9.487 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 22.020 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 0e981934a..2f2fe743b 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:56.585</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:07.590</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>04:09.487</strong>: <a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></li>
-<li><p><strong>00:42.794</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
-<li><p><strong>00:03.688</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
-<li><p><strong>00:00.214</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
-<li><p><strong>00:00.202</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
-<li><p><strong>00:00.199</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>04:22.020</strong>: <a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></li>
+<li><p><strong>00:41.441</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
+<li><p><strong>00:03.547</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
+<li><p><strong>00:00.197</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.194</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.191</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 4fada499d..a8617cd5b 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:12.012</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:10.172</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:10.034</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
-<li><p><strong>00:01.751</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
-<li><p><strong>00:00.226</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
+<li><p><strong>00:08.278</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
+<li><p><strong>00:01.682</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
+<li><p><strong>00:00.212</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 329e7598c..38499012e 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:05.757</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.589</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.103</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
-<li><p><strong>00:01.117</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
-<li><p><strong>00:00.746</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
-<li><p><strong>00:00.733</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
-<li><p><strong>00:00.324</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
-<li><p><strong>00:00.259</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
-<li><p><strong>00:00.242</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
-<li><p><strong>00:00.232</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:02.039</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
+<li><p><strong>00:01.179</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
+<li><p><strong>00:00.708</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
+<li><p><strong>00:00.696</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
+<li><p><strong>00:00.296</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
+<li><p><strong>00:00.230</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
+<li><p><strong>00:00.226</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
+<li><p><strong>00:00.215</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 28086bfdd..1998e7505 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -552,7 +552,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpp40fggce/input0.cc'\nsource_filename = \"/tmp/tmpp40fggce/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpeox3jqg9/input0.cc'\nsource_filename = \"/tmp/tmpeox3jqg9/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/doxygen/classes.html b/docs/reference/api/doxygen/classes.html
index 8d708ab15..83093c6aa 100644
--- a/docs/reference/api/doxygen/classes.html
+++ b/docs/reference/api/doxygen/classes.html
@@ -70,8 +70,8 @@ $(function() {
<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1AccessAnalyzer.html">AccessAnalyzer</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1CorrelationAttrs.html">CorrelationAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1support_1_1Span_1_1iterator__base.h [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1AccessAnalyzerNode.html">AccessAnalyzerNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1CostModel.html">CostModel</a> (<a class="el" href="namespacetvm_1_1meta__schedule.html">tvm::meta_schedule</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_ [...]
<tr><td valign="top"><a class="el" href="structtvm_1_1relay_1_1AdaptivePool1DAttrs.html">AdaptivePool1DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1CostModel.html">CostModel</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1auto__scheduler_1_1AttachMapNode_1_1It [...]
-<tr><td valign="top"><a class="el" href="structtvm_1_1relay_1_1AdaptivePool2DAttrs.html">AdaptivePool2DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1CostModelNode.html">CostModelNode</a> (<a class="el" href="namespacetvm_1_1meta__schedule.html">tvm::meta_schedule</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IterMapExpr.html">IterMap [...]
-<tr><td valign="top"><a class="el" href="structtvm_1_1relay_1_1AdaptivePool3DAttrs.html">AdaptivePool3DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1CostModelNode.html">CostModelNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IterMapExprNode.html"> [...]
+<tr><td valign="top"><a class="el" href="structtvm_1_1relay_1_1AdaptivePool2DAttrs.html">AdaptivePool2DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1CostModelNode.html">CostModelNode</a> (<a class="el" href="namespacetvm_1_1meta__schedule.html">tvm::meta_schedule</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IterMapExpr.html">IterMap [...]
+<tr><td valign="top"><a class="el" href="structtvm_1_1relay_1_1AdaptivePool3DAttrs.html">AdaptivePool3DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1CostModelNode.html">CostModelNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IterMapExprNode.html"> [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1Add.html">Add</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1profiling_1_1CountNode.html">CountNode</a> (<a class="el" href="namespacetvm_1_1runtime_1_1profiling.html">tvm::runtime::profiling</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IterMapResult.html">IterMapResult</a> (<a class="el" hr [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1AddNode.html">AddNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1CropAndResizeAttrs.html">CropAndResizeAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IterMapResultNode.html">IterMapResultNode</a> (<a class="el" href="name [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1ADT.html">ADT</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::runtime</a>)   </td><td rowspan="2" valign="bottom"><a name="letter_d"></a><table border="0" cellspacing="0" cellpadding="0"><tr><td><div class="ah">  d  </div></td></tr></table>
@@ -136,8 +136,8 @@ $(function() {
<tr><td valign="top"><a class="el" href="classtvm_1_1relay_1_1AttrPattern.html">AttrPattern</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1EQNode.html">EQNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html">MatrixSetDiagAttrs</a> (<a class="el" href="namespacetvm_1_1re [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1relay_1_1AttrPatternNode.html">AttrPatternNode</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1ErrorBuilder.html">ErrorBuilder</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1Max.html">Max</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)  [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1AttrRegistry.html">AttrRegistry</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1ErrorReporter.html">ErrorReporter</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1MaxNode.html">MaxNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valig [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1AttrRegistryMap.html">AttrRegistryMap</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1Evaluate.html">Evaluate</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1MaxPool1DAttrs.html">MaxPool1DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay< [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1AttrRegistryMapContainerMap.html">AttrRegistryMapContainerMap</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1EvaluateNode.html">EvaluateNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1MaxPool2DAttrs.html">MaxPool2DAttrs</a> (<a class="el" href="namespa [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1AttrRegistryMap.html">AttrRegistryMap</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1Evaluate.html">Evaluate</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1MaxPool1DAttrs.html">MaxPool1DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay< [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1AttrRegistryMapContainerMap.html">AttrRegistryMapContainerMap</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1EvaluateNode.html">EvaluateNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1MaxPool2DAttrs.html">MaxPool2DAttrs</a> (<a class="el" href="namespa [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1Attrs.html">Attrs</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1vm_1_1Executable.html">Executable</a> (<a class="el" href="namespacetvm_1_1runtime_1_1vm.html">tvm::runtime::vm</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1MaxPool3DAttrs.html">MaxPool3DAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html" [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1AttrsNode.html">AttrsNode</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1Executor.html">Executor</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCallback.html">MeasureCallback</a> (<a class="el" href="namespacetvm_1_1meta__schedule.html [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1detail_1_1AttrsSEqualVisitor.html">AttrsSEqualVisitor</a> (<a class="el" href="namespacetvm_1_1detail.html">tvm::detail</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1ExecutorNode.html">ExecutorNode</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1MeasureCallback.html">MeasureCallback</a> ( [...]
@@ -201,10 +201,10 @@ $(function() {
<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferRealize.html">BufferRealize</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td rowspan="2" valign="bottom"><a name="letter_g"></a><table border="0" cellspacing="0" cellpadding="0"><tr><td><div class="ah">  g  </div></td></tr></table>
</td><td valign="top"><a class="el" href="structtvm_1_1runtime_1_1NullOptType.html">NullOptType</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::runtime</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1ScatterNDAttrs.html">ScatterNDAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="unionTVMValue.html">TVMValue</a>   </td></tr>
<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferRealizeNode.html">BufferRealizeNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td rowspan="2" valign="bottom"><a name="letter_o"></a><table border="0" cellspacing="0" cellpadding="0"><tr><td><div class="ah">  o  </div></td></tr></table>
-</td><td valign="top"><a class="el" href="classtvm_1_1te_1_1Schedule.html">Schedule</a> (<a class="el" href="namespacetvm_1_1te.html">tvm::te</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1Type.html">Type</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td></tr>
-<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferRegion.html">BufferRegion</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1GatherAttrs.html">GatherAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1Schedule.html">Schedule</a> (<a class="el" href="namespacetvm_1_1tir.html">tv [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferRegionNode.html">BufferRegionNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1GatherNDAttrs.html">GatherNDAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1ObjAllocatorBase.html">ObjAllocatorBase</a> (<a class="el" hr [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferStore.html">BufferStore</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1GE.html">GE</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1Object.html">Object</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::runtime</a>) &# [...]
+</td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1Schedule.html">Schedule</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1Type.html">Type</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td></tr>
+<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferRegion.html">BufferRegion</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1GatherAttrs.html">GatherAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1te_1_1Schedule.html">Schedule</a> (<a class="el" href="namespacetvm_1_1te.html">tvm: [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferRegionNode.html">BufferRegionNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1GatherNDAttrs.html">GatherNDAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1ObjAllocatorBase.html">ObjAllocatorBase</a> (<a class="el" hr [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferStore.html">BufferStore</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1GE.html">GE</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1Object.html">Object</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::runtime</a>) &# [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1tir_1_1BufferStoreNode.html">BufferStoreNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1GenericFunc.html">GenericFunc</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1runtime_1_1ObjectEqual.html">ObjectEqual</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::ru [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1Builder.html">Builder</a> (<a class="el" href="namespacetvm_1_1meta__schedule.html">tvm::meta_schedule</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1GenericFuncNode.html">GenericFuncNode</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1runtime_1_1ObjectHash.html">ObjectHash</a> (<a class="el" href="namespacetvm_1_ [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1BuilderInput.html">BuilderInput</a> (<a class="el" href="namespacetvm_1_1meta__schedule.html">tvm::meta_schedule</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1GENode.html">GENode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html">ObjectPtr</a> (<a class="el" href="namespa [...]
@@ -252,11 +252,11 @@ $(function() {
<tr><td valign="top"><a class="el" href="classtvm_1_1CompileError.html">CompileError</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1detail_1_1ImplSHashReduce_3_01T_00_01true_01_4.html">ImplSHashReduce< T, true ></a> (<a class="el" href="namespacetvm_1_1detail.html">tvm::detail</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1PadAttrs.html">PadAttrs</a> (<a class="el" h [...]
<tr><td valign="top"><a class="el" href="structtvm_1_1relay_1_1CompilerAttrs.html">CompilerAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1detail_1_1ImplVisitAttrs.html">ImplVisitAttrs</a> (<a class="el" href="namespacetvm_1_1detail.html">tvm::detail</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> (<a class="el" href="namespacetvm [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeAtStep.html">ComputeAtStep</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1detail_1_1ImplVisitAttrs_3_01T_00_01true_01_4.html">ImplVisitAttrs< T, true ></a> (<a class="el" href="namespacetvm_1_1detail.html">tvm::detail</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1 [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeAtStepNode.html">ComputeAtStepNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1IncompleteType.html">IncompleteType</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1transform_1_1PassContextNode.html">PassContextNode</a> (<a [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeDAG.html">ComputeDAG</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1IncompleteTypeNode.html">IncompleteTypeNode</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1transform_1_1PassInfo.html">PassInfo</a> (<a class="el" href="nam [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeAtStepNode.html">ComputeAtStepNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1IncompleteType.html">IncompleteType</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1transform_1_1PassContextNode.html">PassContextNode</a> (<a [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeDAG.html">ComputeDAG</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1IncompleteTypeNode.html">IncompleteTypeNode</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1transform_1_1PassInfo.html">PassInfo</a> (<a class="el" href="nam [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeDAGNode.html">ComputeDAGNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1IndexMap.html">IndexMap</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1transform_1_1PassInfoNode.html">PassInfoNode</a> (<a class [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeInlineStep.html">ComputeInlineStep</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1IndexMapNode.html">IndexMapNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1instrument_1_1PassInstrument.html">PassInstr [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeInlineStepNode.html">ComputeInlineStepNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1InitOpAttrs.html">InitOpAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1instrument_1_1PassInstrumentNod [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeInlineStep.html">ComputeInlineStep</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1tir_1_1IndexMapNode.html">IndexMapNode</a> (<a class="el" href="namespacetvm_1_1tir.html">tvm::tir</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1instrument_1_1PassInstrument.html">PassInstr [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeInlineStepNode.html">ComputeInlineStepNode</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1InitOpAttrs.html">InitOpAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1instrument_1_1PassInstrumentNod [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1te_1_1ComputeOp.html">ComputeOp</a> (<a class="el" href="namespacetvm_1_1te.html">tvm::te</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1InplaceArrayBase.html">InplaceArrayBase</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::runtime</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1transform_1_1PassNode.html">PassNode</a> (<a class="el" href="namespacetvm_1_1 [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1te_1_1ComputeOpNode.html">ComputeOpNode</a> (<a class="el" href="namespacetvm_1_1te.html">tvm::te</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1relay_1_1InstanceNormAttrs.html">InstanceNormAttrs</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1Pattern.html">Pattern</a> (<a class="el" href="namespacetvm_1_1r [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1auto__scheduler_1_1ComputeRootStep.html">ComputeRootStep</a> (<a class="el" href="namespacetvm_1_1auto__scheduler.html">tvm::auto_scheduler</a>)   </td><td valign="top"><a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html">Instruction</a> (<a class="el" href="namespacetvm_1_1runtime_1_1vm.html">tvm::runtime::vm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1PatternConst [...]
@@ -272,8 +272,8 @@ $(function() {
<tr><td valign="top"><a class="el" href="classtvm_1_1arith_1_1ConstIntBoundNode.html">ConstIntBoundNode</a> (<a class="el" href="namespacetvm_1_1arith.html">tvm::arith</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IntConstraintsTransformNode.html">IntConstraintsTransformNode</a> (<a class="el" href="namespacetvm_1_1arith.html">tvm::arith</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1PatternVarNode.html">Pattern [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1arith_1_1ConstraintContext.html">ConstraintContext</a> (<a class="el" href="namespacetvm_1_1arith.html">tvm::arith</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1Integer.html">Integer</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1PatternVisitor.html">PatternVisitor</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm: [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1Constructor.html">Constructor</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1InterpreterClosure.html">InterpreterClosure</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1PatternWildcard.html">PatternWildcard</a> (<a class="el" href="namespacetvm_1_1rela [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1ConstructorNode.html">ConstructorNode</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1InterpreterClosureObj.html">InterpreterClosureObj</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1PatternWildcardNode.html">PatternWildcardNode</a> (<a class="el" href [...]
-<tr><td valign="top"><a class="el" href="classtvm_1_1relay_1_1ConstructorValue.html">ConstructorValue</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IntGroupBounds.html">IntGroupBounds</a> (<a class="el" href="namespacetvm_1_1arith.html">tvm::arith</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1profiling_1_1PercentNode.html">PercentNode</a> (<a cla [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1ConstructorNode.html">ConstructorNode</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1InterpreterClosureObj.html">InterpreterClosureObj</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1relay_1_1PatternWildcardNode.html">PatternWildcardNode</a> (<a class="el" href [...]
+<tr><td valign="top"><a class="el" href="classtvm_1_1relay_1_1ConstructorValue.html">ConstructorValue</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IntGroupBounds.html">IntGroupBounds</a> (<a class="el" href="namespacetvm_1_1arith.html">tvm::arith</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1profiling_1_1PercentNode.html">PercentNode</a> (<a cla [...]
<tr><td valign="top"><a class="el" href="structtvm_1_1relay_1_1ConstructorValueObj.html">ConstructorValueObj</a> (<a class="el" href="namespacetvm_1_1relay.html">tvm::relay</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1arith_1_1IntGroupBoundsNode.html">IntGroupBoundsNode</a> (<a class="el" href="namespacetvm_1_1arith.html">tvm::arith</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1te_1_1PlaceholderOp.html">PlaceholderOp</a> (<a cl [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1NDArray_1_1Container.html">NDArray::Container</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::runtime</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1IntImm.html">IntImm</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1te_1_1PlaceholderOpNode.html">PlaceholderOpNode</a> (<a class="el" href="namespacetvm_1_1te.ht [...]
<tr><td valign="top"><a class="el" href="classtvm_1_1runtime_1_1NDArray_1_1ContainerBase.html">NDArray::ContainerBase</a> (<a class="el" href="namespacetvm_1_1runtime.html">tvm::runtime</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1IntImmNode.html">IntImmNode</a> (<a class="el" href="namespacetvm.html">tvm</a>)   </td><td valign="top"><a class="el" href="classtvm_1_1PointerType.html">PointerType</a> (<a class="el" href="namespacetvm.html">tvm< [...]
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode-members.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode-members.html
index 196c03b0d..27b0aaa02 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode-members.html
@@ -88,7 +88,7 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a9e84841ca982bff376a978ade0132631">FDeleter</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a87e2f696bcd7ab1c4066487f4cba7d29">FGenerateMeasureCandidates</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#acf145edd9c5a047166dd8f29f65ab75e">FInitializeWithTuneContext</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">FNotifyRunnerResults</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">FNotifyRunnerResults</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#ad4730dca4fcd0cfbd73fc6c9ed11fe4a">FPostTuning</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a528df580fe251d7fe9eec1e68f8d2385">FPreTuning</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#ad565f2d8d7b6908f92b34aea6f478fd3">GenerateMeasureCandidates</a>() final</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
@@ -98,7 +98,7 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#afcc701ca7cbb2a80ebe59428bd422946">InitializeWithTuneContext</a>(const TuneContext &context) final</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a404a53311309ba8e782a0a0c07e96d19">NotifyRunnerResults</a>(const TuneContext &context, const Array< MeasureCandidate > &measure_candidates, const Array< RunnerResult > &results)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"><span class="mlabel">vir [...]
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a6ae774bd7a6caedf58152c562dae5378">NotifyRunnerResults</a>(const Array< MeasureCandidate > &measure_candidates, const Array< RunnerResult > &results)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">tvm::meta_schedule::PySearchStrategyNode</a></td><td class="entry"><span class="mlabel">virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a133436a9ec5c4a768b94102bf95a660b">Object</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html
index 8dcf1924c..782d91791 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html
@@ -86,7 +86,7 @@ Inheritance diagram for tvm::meta_schedule::PySearchStrategyNode:</div>
<div class="dynheader">
Collaboration diagram for tvm::meta_schedule::PySearchStrategyNode:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1PySearchStrategyNode__coll__graph.svg" width="1563" height="1015"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1PySearchStrategyNode__coll__graph.svg" width="1531" height="1015"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<table class="memberdecls">
@@ -104,9 +104,9 @@ Public Types</h2></td></tr>
<tr class="memitem:a87e2f696bcd7ab1c4066487f4cba7d29"><td class="memItemLeft" align="right" valign="top">using </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a87e2f696bcd7ab1c4066487f4cba7d29">FGenerateMeasureCandidates</a> = <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a>< <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" [...]
<tr class="memdesc:a87e2f696bcd7ab1c4066487f4cba7d29"><td class="mdescLeft"> </td><td class="mdescRight">The function type of <code>GenerateMeasureCandidates</code> method. <a href="#a87e2f696bcd7ab1c4066487f4cba7d29">More...</a><br /></td></tr>
<tr class="separator:a87e2f696bcd7ab1c4066487f4cba7d29"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a802c0ead40a90b4bf5c0962a8d4bbdee"><td class="memItemLeft" align="right" valign="top">using </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">FNotifyRunnerResults</a> = <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a>< void(const <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContext.html">TuneContext</a> [...]
-<tr class="memdesc:a802c0ead40a90b4bf5c0962a8d4bbdee"><td class="mdescLeft"> </td><td class="mdescRight">The function type of <code>NotifyRunnerResults</code> method. <a href="#a802c0ead40a90b4bf5c0962a8d4bbdee">More...</a><br /></td></tr>
-<tr class="separator:a802c0ead40a90b4bf5c0962a8d4bbdee"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:abfcbc3d1df5bb6d93c0773b069f0eae4"><td class="memItemLeft" align="right" valign="top">using </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">FNotifyRunnerResults</a> = <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a>< void(const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" [...]
+<tr class="memdesc:abfcbc3d1df5bb6d93c0773b069f0eae4"><td class="mdescLeft"> </td><td class="mdescRight">The function type of <code>NotifyRunnerResults</code> method. <a href="#abfcbc3d1df5bb6d93c0773b069f0eae4">More...</a><br /></td></tr>
+<tr class="separator:abfcbc3d1df5bb6d93c0773b069f0eae4"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="inherit_header pub_types_classtvm_1_1runtime_1_1Object"><td colspan="2" onclick="javascript:toggleInherit('pub_types_classtvm_1_1runtime_1_1Object')"><img src="closed.png" alt="-"/> Public Types inherited from <a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td></tr>
<tr class="memitem:a9e84841ca982bff376a978ade0132631 inherit pub_types_classtvm_1_1runtime_1_1Object"><td class="memItemLeft" align="right" valign="top">typedef void(* </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a9e84841ca982bff376a978ade0132631">FDeleter</a>) (<a class="el" href="classtvm_1_1runtime_1_1Object.html">Object</a> *self)</td></tr>
<tr class="memdesc:a9e84841ca982bff376a978ade0132631 inherit pub_types_classtvm_1_1runtime_1_1Object"><td class="mdescLeft"> </td><td class="mdescRight"><a class="el" href="classtvm_1_1runtime_1_1Object.html" title="base class of all object containers. ">Object</a> deleter. <a href="classtvm_1_1runtime_1_1Object.html#a9e84841ca982bff376a978ade0132631">More...</a><br /></td></tr>
@@ -130,9 +130,9 @@ Public Member Functions</h2></td></tr>
<tr class="memitem:ad565f2d8d7b6908f92b34aea6f478fd3"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#ad565f2d8d7b [...]
<tr class="memdesc:ad565f2d8d7b6908f92b34aea6f478fd3"><td class="mdescLeft"> </td><td class="mdescRight">Generate measure candidates from design spaces for measurement. <a href="#ad565f2d8d7b6908f92b34aea6f478fd3">More...</a><br /></td></tr>
<tr class="separator:ad565f2d8d7b6908f92b34aea6f478fd3"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a404a53311309ba8e782a0a0c07e96d19"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a404a53311309ba8e782a0a0c07e96d19">NotifyRunnerResults</a> (const <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContext.html">TuneContext</a> &context, const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" hr [...]
-<tr class="memdesc:a404a53311309ba8e782a0a0c07e96d19"><td class="mdescLeft"> </td><td class="mdescRight">Update the search strategy with measurement results. <a href="#a404a53311309ba8e782a0a0c07e96d19">More...</a><br /></td></tr>
-<tr class="separator:a404a53311309ba8e782a0a0c07e96d19"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a6ae774bd7a6caedf58152c562dae5378"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a6ae774bd7a6caedf58152c562dae5378">NotifyRunnerResults</a> (const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > &measure_candidat [...]
+<tr class="memdesc:a6ae774bd7a6caedf58152c562dae5378"><td class="mdescLeft"> </td><td class="mdescRight">Update the search strategy with measurement results. <a href="#a6ae774bd7a6caedf58152c562dae5378">More...</a><br /></td></tr>
+<tr class="separator:a6ae774bd7a6caedf58152c562dae5378"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a0d297d00332272c24f7052c3b348f66c"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a0d297d00332272c24f7052c3b348f66c">TVM_DECLARE_FINAL_OBJECT_INFO</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html">PySearchStrategyNode</a>, <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html">SearchStrat [...]
<tr class="separator:a0d297d00332272c24f7052c3b348f66c"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="inherit_header pub_methods_classtvm_1_1meta__schedule_1_1SearchStrategyNode"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1meta__schedule_1_1SearchStrategyNode')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html">tvm::meta_schedule::SearchStrategyNode</a></td></tr>
@@ -178,7 +178,7 @@ Public Attributes</h2></td></tr>
<tr class="memitem:a5fdfb43b58d50fc34d8c515c9c9b7398"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a87e2f696bcd7ab1c4066487f4cba7d29">FGenerateMeasureCandidates</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a5fdfb43b58d50fc34d8c515c9c9b7398">f_generate_measure_candidates</a></td></tr>
<tr class="memdesc:a5fdfb43b58d50fc34d8c515c9c9b7398"><td class="mdescLeft"> </td><td class="mdescRight">The packed function to the <code>GenerateMeasureCandidates</code> method. <a href="#a5fdfb43b58d50fc34d8c515c9c9b7398">More...</a><br /></td></tr>
<tr class="separator:a5fdfb43b58d50fc34d8c515c9c9b7398"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:aa89eabbd32979cdec2bee83d980350c7"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">FNotifyRunnerResults</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#aa89eabbd32979cdec2bee83d980350c7">f_notify_runner_results</a></td></tr>
+<tr class="memitem:aa89eabbd32979cdec2bee83d980350c7"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">FNotifyRunnerResults</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#aa89eabbd32979cdec2bee83d980350c7">f_notify_runner_results</a></td></tr>
<tr class="memdesc:aa89eabbd32979cdec2bee83d980350c7"><td class="mdescLeft"> </td><td class="mdescRight">The packed function to the <code>NotifyRunnerResults</code> method. <a href="#aa89eabbd32979cdec2bee83d980350c7">More...</a><br /></td></tr>
<tr class="separator:aa89eabbd32979cdec2bee83d980350c7"><td class="memSeparator" colspan="2"> </td></tr>
</table><table class="memberdecls">
@@ -287,14 +287,14 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="a802c0ead40a90b4bf5c0962a8d4bbdee"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a802c0ead40a90b4bf5c0962a8d4bbdee">◆ </a></span>FNotifyRunnerResults</h2>
+<a id="abfcbc3d1df5bb6d93c0773b069f0eae4"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#abfcbc3d1df5bb6d93c0773b069f0eae4">◆ </a></span>FNotifyRunnerResults</h2>
<div class="memitem">
<div class="memproto">
<table class="memname">
<tr>
- <td class="memname">using <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">tvm::meta_schedule::PySearchStrategyNode::FNotifyRunnerResults</a> = <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a><void( const <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContext.html">TuneContext</a>&, const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a><<a [...]
+ <td class="memname">using <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">tvm::meta_schedule::PySearchStrategyNode::FNotifyRunnerResults</a> = <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a><void(const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a><<a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a>>&a [...]
</tr>
</table>
</div><div class="memdoc">
@@ -415,8 +415,8 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="a404a53311309ba8e782a0a0c07e96d19"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a404a53311309ba8e782a0a0c07e96d19">◆ </a></span>NotifyRunnerResults()</h2>
+<a id="a6ae774bd7a6caedf58152c562dae5378"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a6ae774bd7a6caedf58152c562dae5378">◆ </a></span>NotifyRunnerResults()</h2>
<div class="memitem">
<div class="memproto">
@@ -427,12 +427,6 @@ Additional Inherited Members</h2></td></tr>
<tr>
<td class="memname">void tvm::meta_schedule::PySearchStrategyNode::NotifyRunnerResults </td>
<td>(</td>
- <td class="paramtype">const <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContext.html">TuneContext</a> & </td>
- <td class="paramname"><em>context</em>, </td>
- </tr>
- <tr>
- <td class="paramkey"></td>
- <td></td>
<td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > & </td>
<td class="paramname"><em>measure_candidates</em>, </td>
</tr>
@@ -458,14 +452,13 @@ Additional Inherited Members</h2></td></tr>
<p>Update the search strategy with measurement results. </p>
<dl class="params"><dt>Parameters</dt><dd>
<table class="params">
- <tr><td class="paramname">context</td><td>The tuning context. </td></tr>
<tr><td class="paramname">measure_candidates</td><td>The candidates to be measured. </td></tr>
<tr><td class="paramname">results</td><td>The measurement results from the runner. </td></tr>
</table>
</dd>
</dl>
-<p>Implements <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a609a8697917c6041af77478c8f4ef34c">tvm::meta_schedule::SearchStrategyNode</a>.</p>
+<p>Implements <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a1a5a62e39bbe941f13ec784b43d7e169">tvm::meta_schedule::SearchStrategyNode</a>.</p>
</div>
</div>
@@ -670,7 +663,7 @@ Additional Inherited Members</h2></td></tr>
<div class="memproto">
<table class="memname">
<tr>
- <td class="memname"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">FNotifyRunnerResults</a> tvm::meta_schedule::PySearchStrategyNode::f_notify_runner_results</td>
+ <td class="memname"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">FNotifyRunnerResults</a> tvm::meta_schedule::PySearchStrategyNode::f_notify_runner_results</td>
</tr>
</table>
</div><div class="memdoc">
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode__coll__graph.svg
index 77c23f2fb..0c53179b3 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1PySearchStrategyNode__coll__graph.svg
@@ -4,27 +4,27 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::meta_schedule::PySearchStrategyNode Pages: 1 -->
-<svg width="1172pt" height="761pt"
- viewBox="0.00 0.00 1172.00 761.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<svg width="1148pt" height="761pt"
+ viewBox="0.00 0.00 1148.00 761.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 757)">
<title>tvm::meta_schedule::PySearchStrategyNode</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-757 1168,-757 1168,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-757 1144,-757 1144,4 -4,4"/>
<!-- Node3 -->
<g id="node1" class="node">
<title>Node3</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="455,-.5 455,-134.5 664,-134.5 664,-.5 455,-.5"/>
-<text text-anchor="start" x="463" y="-122.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
-<text text-anchor="middle" x="559.5" y="-111.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::PySearchStrategyNode</text>
-<polyline fill="none" stroke="#000000" points="455,-104.5 664,-104.5 "/>
-<text text-anchor="start" x="463" y="-92.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<polyline fill="none" stroke="#000000" points="455,-85.5 664,-85.5 "/>
-<text text-anchor="start" x="463" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
-<text text-anchor="start" x="463" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitializeWithTuneContext()</text>
-<text text-anchor="start" x="463" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PreTuning()</text>
-<text text-anchor="start" x="463" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PostTuning()</text>
-<text text-anchor="start" x="463" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GenerateMeasureCandidates()</text>
-<text text-anchor="start" x="463" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ NotifyRunnerResults()</text>
-<text text-anchor="start" x="463" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="472,-.5 472,-134.5 681,-134.5 681,-.5 472,-.5"/>
+<text text-anchor="start" x="480" y="-122.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
+<text text-anchor="middle" x="576.5" y="-111.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::PySearchStrategyNode</text>
+<polyline fill="none" stroke="#000000" points="472,-104.5 681,-104.5 "/>
+<text text-anchor="start" x="480" y="-92.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<polyline fill="none" stroke="#000000" points="472,-85.5 681,-85.5 "/>
+<text text-anchor="start" x="480" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
+<text text-anchor="start" x="480" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitializeWithTuneContext()</text>
+<text text-anchor="start" x="480" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PreTuning()</text>
+<text text-anchor="start" x="480" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PostTuning()</text>
+<text text-anchor="start" x="480" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GenerateMeasureCandidates()</text>
+<text text-anchor="start" x="480" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ NotifyRunnerResults()</text>
+<text text-anchor="start" x="480" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
</g>
<!-- Node4 -->
<g id="node2" class="node">
@@ -49,8 +49,8 @@
<!-- Node4->Node3 -->
<g id="edge1" class="edge">
<title>Node4->Node3</title>
-<path fill="none" stroke="#191970" d="M216.267,-192.7741C299.7957,-153.4555 387.8047,-121.9285 454.6358,-99.9115"/>
-<polygon fill="none" stroke="#191970" points="214.6859,-189.6503 207.1554,-197.103 217.6899,-195.973 214.6859,-189.6503"/>
+<path fill="none" stroke="#191970" d="M216.3186,-192.7674C305.7314,-151.5471 401.0488,-119.3378 471.9326,-97.5218"/>
+<polygon fill="none" stroke="#191970" points="214.7168,-189.6524 207.1285,-197.0462 217.6714,-195.9983 214.7168,-189.6524"/>
</g>
<!-- Node5 -->
<g id="node3" class="node">
@@ -126,100 +126,100 @@
<!-- Node6->Node3 -->
<g id="edge4" class="edge">
<title>Node6->Node3</title>
-<path fill="none" stroke="#404040" d="M328.5593,-220.9424C345.9862,-199.0665 369.5614,-172.4578 394.5,-153 409.6667,-141.1665 426.7193,-130.2071 443.9564,-120.3567"/>
-<polygon fill="none" stroke="#404040" points="444.2163,-120.2119 447.5093,-113.7965 454.6976,-114.3688 451.4047,-120.7841 444.2163,-120.2119"/>
-<text text-anchor="start" x="394.5" y="-167" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_generate_measure</text>
-<text text-anchor="middle" x="450.5" y="-156" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_candidates</text>
+<path fill="none" stroke="#404040" d="M330.2442,-220.7629C348.6386,-198.829 373.453,-172.2221 399.5,-153 418.2922,-139.1318 439.6865,-126.568 460.9487,-115.6024"/>
+<polygon fill="none" stroke="#404040" points="460.9852,-115.584 464.5426,-109.3115 471.7009,-110.1827 468.1435,-116.4553 460.9852,-115.584"/>
+<text text-anchor="start" x="399.5" y="-167" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_generate_measure</text>
+<text text-anchor="middle" x="455.5" y="-156" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_candidates</text>
</g>
<!-- Node7 -->
<g id="node5" class="node">
<title>Node7</title>
-<g id="a_node5"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void()\>\n||}">
-<polygon fill="#ffffff" stroke="#000000" points="392,-226.5 392,-294.5 541,-294.5 541,-226.5 392,-226.5"/>
-<text text-anchor="start" x="400" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
-<text text-anchor="middle" x="466.5" y="-271.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void()></text>
-<polyline fill="none" stroke="#000000" points="392,-264.5 541,-264.5 "/>
-<text text-anchor="middle" x="466.5" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="392,-245.5 541,-245.5 "/>
-<text text-anchor="middle" x="466.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<g id="a_node5"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void(const Array\l\< MeasureCandidate \> &,\l const Array\< RunnerResult \> &)\>\n||}">
+<polygon fill="#ffffff" stroke="#000000" points="392.5,-215.5 392.5,-305.5 576.5,-305.5 576.5,-215.5 392.5,-215.5"/>
+<text text-anchor="start" x="400.5" y="-293.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
+<text text-anchor="start" x="400.5" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const Array</text>
+<text text-anchor="start" x="400.5" y="-271.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< MeasureCandidate > &,</text>
+<text text-anchor="middle" x="484.5" y="-260.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> const Array< RunnerResult > &)></text>
+<polyline fill="none" stroke="#000000" points="392.5,-253.5 576.5,-253.5 "/>
+<text text-anchor="middle" x="484.5" y="-241.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="392.5,-234.5 576.5,-234.5 "/>
+<text text-anchor="middle" x="484.5" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
</a>
</g>
</g>
<!-- Node7->Node3 -->
<g id="edge5" class="edge">
<title>Node7->Node3</title>
-<path fill="none" stroke="#404040" d="M482.9125,-226.4397C493.6846,-204.0847 508.2319,-173.8951 521.7544,-145.8322"/>
-<polygon fill="none" stroke="#404040" points="521.8649,-145.6029 520.866,-138.4613 527.0741,-134.7925 528.073,-141.9341 521.8649,-145.6029"/>
-<text text-anchor="middle" x="555.5" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_post_tuning</text>
+<path fill="none" stroke="#404040" d="M498.5184,-215.4532C505.1988,-195.8792 513.8421,-172.9187 523.5,-153 524.6763,-150.5741 525.9034,-148.1298 527.1709,-145.6782"/>
+<polygon fill="none" stroke="#404040" points="527.274,-145.4865 526.5915,-138.3078 532.9555,-134.9167 533.638,-142.0955 527.274,-145.4865"/>
+<text text-anchor="middle" x="585.5" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_notify_runner_results</text>
</g>
<!-- Node8 -->
<g id="node6" class="node">
<title>Node8</title>
-<g id="a_node6"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void(const TuneContext &)\>\n||}">
-<polygon fill="#ffffff" stroke="#000000" points="559,-226.5 559,-294.5 746,-294.5 746,-226.5 559,-226.5"/>
-<text text-anchor="start" x="567" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
-<text text-anchor="middle" x="652.5" y="-271.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const TuneContext &)></text>
-<polyline fill="none" stroke="#000000" points="559,-264.5 746,-264.5 "/>
-<text text-anchor="middle" x="652.5" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="559,-245.5 746,-245.5 "/>
-<text text-anchor="middle" x="652.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<g id="a_node6"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void()\>\n||}">
+<polygon fill="#ffffff" stroke="#000000" points="595,-226.5 595,-294.5 744,-294.5 744,-226.5 595,-226.5"/>
+<text text-anchor="start" x="603" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
+<text text-anchor="middle" x="669.5" y="-271.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void()></text>
+<polyline fill="none" stroke="#000000" points="595,-264.5 744,-264.5 "/>
+<text text-anchor="middle" x="669.5" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="595,-245.5 744,-245.5 "/>
+<text text-anchor="middle" x="669.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
</a>
</g>
</g>
<!-- Node8->Node3 -->
<g id="edge6" class="edge">
<title>Node8->Node3</title>
-<path fill="none" stroke="#404040" d="M636.0875,-226.4397C625.3154,-204.0847 610.7681,-173.8951 597.2456,-145.8322"/>
-<polygon fill="none" stroke="#404040" points="597.1351,-145.6029 590.927,-141.9341 591.9259,-134.7925 598.134,-138.4613 597.1351,-145.6029"/>
-<text text-anchor="start" x="608.5" y="-167" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_initialize_with</text>
-<text text-anchor="middle" x="653" y="-156" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_tune_context</text>
+<path fill="none" stroke="#404040" d="M666.7978,-226.2069C664.0544,-204.3889 658.5444,-176.0141 647.5,-153 646.1852,-150.2603 644.7635,-147.534 643.2529,-144.83"/>
+<polygon fill="none" stroke="#404040" points="643.2333,-144.7976 636.7059,-141.7328 637.0244,-134.5287 643.5518,-137.5935 643.2333,-144.7976"/>
+<text text-anchor="middle" x="693.5" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_post_tuning</text>
</g>
<!-- Node9 -->
<g id="node7" class="node">
<title>Node9</title>
-<g id="a_node7"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void(const Array\l\< tir::Schedule \> &, const\l Optional\< Database \> &, const\l Optional\< CostModel \> &)\>\n||}">
-<polygon fill="#ffffff" stroke="#000000" points="764,-210 764,-311 937,-311 937,-210 764,-210"/>
-<text text-anchor="start" x="772" y="-299" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
-<text text-anchor="start" x="772" y="-288" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const Array</text>
-<text text-anchor="start" x="772" y="-277" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tir::Schedule > &, const</text>
-<text text-anchor="start" x="772" y="-266" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> Optional< Database > &, const</text>
-<text text-anchor="middle" x="850.5" y="-255" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> Optional< CostModel > &)></text>
-<polyline fill="none" stroke="#000000" points="764,-248 937,-248 "/>
-<text text-anchor="middle" x="850.5" y="-236" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="764,-229 937,-229 "/>
-<text text-anchor="middle" x="850.5" y="-217" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<g id="a_node7"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void(const TuneContext &)\>\n||}">
+<polygon fill="#ffffff" stroke="#000000" points="762,-226.5 762,-294.5 949,-294.5 949,-226.5 762,-226.5"/>
+<text text-anchor="start" x="770" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
+<text text-anchor="middle" x="855.5" y="-271.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const TuneContext &)></text>
+<polyline fill="none" stroke="#000000" points="762,-264.5 949,-264.5 "/>
+<text text-anchor="middle" x="855.5" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="762,-245.5 949,-245.5 "/>
+<text text-anchor="middle" x="855.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
</a>
</g>
</g>
<!-- Node9->Node3 -->
<g id="edge7" class="edge">
<title>Node9->Node3</title>
-<path fill="none" stroke="#404040" d="M782.7189,-209.7872C757.5363,-191.429 728.5196,-170.8372 701.5,-153 692.7756,-147.2405 683.6678,-141.3939 674.4611,-135.6009"/>
-<polygon fill="none" stroke="#404040" points="674.2169,-135.4484 667.0089,-135.6619 664.0395,-129.0906 671.2474,-128.877 674.2169,-135.4484"/>
-<text text-anchor="middle" x="767" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_pre_tuning</text>
+<path fill="none" stroke="#404040" d="M822.2416,-226.383C799.3579,-203.967 767.5901,-174.8555 736.5,-153 722.4738,-143.1399 707.1778,-133.6071 691.7864,-124.7082"/>
+<polygon fill="none" stroke="#404040" points="691.5631,-124.5813 684.3703,-125.0946 681.13,-118.6524 688.3228,-118.1392 691.5631,-124.5813"/>
+<text text-anchor="start" x="763.5" y="-167" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_initialize_with</text>
+<text text-anchor="middle" x="808" y="-156" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_tune_context</text>
</g>
<!-- Node10 -->
<g id="node8" class="node">
<title>Node10</title>
-<g id="a_node8"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void(const TuneContext\l &, const Array\< MeasureCandidate\l \> &, const Array\< RunnerResult \> &)\>\n||}">
-<polygon fill="#ffffff" stroke="#000000" points="955,-215.5 955,-305.5 1164,-305.5 1164,-215.5 955,-215.5"/>
-<text text-anchor="start" x="963" y="-293.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
-<text text-anchor="start" x="963" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const TuneContext</text>
-<text text-anchor="start" x="963" y="-271.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> &, const Array< MeasureCandidate</text>
-<text text-anchor="middle" x="1059.5" y="-260.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> > &, const Array< RunnerResult > &)></text>
-<polyline fill="none" stroke="#000000" points="955,-253.5 1164,-253.5 "/>
-<text text-anchor="middle" x="1059.5" y="-241.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="955,-234.5 1164,-234.5 "/>
-<text text-anchor="middle" x="1059.5" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<g id="a_node8"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="{tvm::runtime::TypedPacked\lFunc\< void(const Array\l\< tir::Schedule \> &, const\l Optional\< Database \> &, const\l Optional\< CostModel \> &)\>\n||}">
+<polygon fill="#ffffff" stroke="#000000" points="967,-210 967,-311 1140,-311 1140,-210 967,-210"/>
+<text text-anchor="start" x="975" y="-299" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
+<text text-anchor="start" x="975" y="-288" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const Array</text>
+<text text-anchor="start" x="975" y="-277" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tir::Schedule > &, const</text>
+<text text-anchor="start" x="975" y="-266" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> Optional< Database > &, const</text>
+<text text-anchor="middle" x="1053.5" y="-255" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> Optional< CostModel > &)></text>
+<polyline fill="none" stroke="#000000" points="967,-248 1140,-248 "/>
+<text text-anchor="middle" x="1053.5" y="-236" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="967,-229 1140,-229 "/>
+<text text-anchor="middle" x="1053.5" y="-217" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
</a>
</g>
</g>
<!-- Node10->Node3 -->
<g id="edge8" class="edge">
<title>Node10->Node3</title>
-<path fill="none" stroke="#404040" d="M989.6861,-215.4983C975.6856,-207.4233 960.8582,-199.5161 946.5,-193 858.5566,-153.0894 754.1564,-120.0105 675.9661,-97.8509"/>
-<polygon fill="none" stroke="#404040" points="675.6896,-97.7732 668.8308,-99.9999 664.1375,-94.5251 670.9963,-92.2985 675.6896,-97.7732"/>
-<text text-anchor="middle" x="957.5" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_notify_runner_results</text>
+<path fill="none" stroke="#404040" d="M986.5596,-209.9306C977.3498,-203.8719 967.8433,-198.0527 958.5,-193 874.3968,-147.5182 770.9378,-114.7792 692.9106,-94.167"/>
+<polygon fill="none" stroke="#404040" points="692.7132,-94.1156 685.8981,-96.4727 681.1012,-91.0885 687.9162,-88.7314 692.7132,-94.1156"/>
+<text text-anchor="middle" x="956" y="-161.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +f_pre_tuning</text>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategy.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategy.html
index c8c080d4f..932650bcd 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategy.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategy.html
@@ -128,7 +128,7 @@ Public Member Functions</h2></td></tr>
</table><table class="memberdecls">
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pub-static-methods"></a>
Static Public Member Functions</h2></td></tr>
-<tr class="memitem:a95eb75dce8960913ed0d390ba38c612f"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html">SearchStrategy</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html#a95eb75dce8960913ed0d390ba38c612f">PySearchStrategy</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#acf145edd9c5a047166dd8f29f65ab75e">P [...]
+<tr class="memitem:a95eb75dce8960913ed0d390ba38c612f"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html">SearchStrategy</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html#a95eb75dce8960913ed0d390ba38c612f">PySearchStrategy</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#acf145edd9c5a047166dd8f29f65ab75e">P [...]
<tr class="memdesc:a95eb75dce8960913ed0d390ba38c612f"><td class="mdescLeft"> </td><td class="mdescRight">Create a search strategy with customized methods on the python-side. <a href="#a95eb75dce8960913ed0d390ba38c612f">More...</a><br /></td></tr>
<tr class="separator:a95eb75dce8960913ed0d390ba38c612f"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a2a9e2eb2936790c137938ae6c2c950c5"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html">SearchStrategy</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html#a2a9e2eb2936790c137938ae6c2c950c5">ReplayTrace</a> (int num_trials_per_iter, int max_trials_per_task, int max_fail_count)</td></tr>
@@ -304,7 +304,7 @@ Additional Inherited Members</h2></td></tr>
<tr>
<td class="paramkey"></td>
<td></td>
- <td class="paramtype"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">PySearchStrategyNode::FNotifyRunnerResults</a> </td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">PySearchStrategyNode::FNotifyRunnerResults</a> </td>
<td class="paramname"><em>f_notify_runner_results</em> </td>
</tr>
<tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode-members.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode-members.html
index c8b8f2b61..f1cac641f 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode-members.html
@@ -88,7 +88,7 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a76f812f41229a0a8a3e43b5fa052b26f">InitializeWithTuneContext</a>(const TuneContext &context)=0</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html">tvm::meta_schedule::SearchStrategyNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a609a8697917c6041af77478c8f4ef34c">NotifyRunnerResults</a>(const TuneContext &context, const Array< MeasureCandidate > &measure_candidates, const Array< RunnerResult > &results)=0</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html">tvm::meta_schedule::SearchStrategyNode</a></td><td class="entry"><span class="mlabel">pure vi [...]
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a1a5a62e39bbe941f13ec784b43d7e169">NotifyRunnerResults</a>(const Array< MeasureCandidate > &measure_candidates, const Array< RunnerResult > &results)=0</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html">tvm::meta_schedule::SearchStrategyNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a133436a9ec5c4a768b94102bf95a660b">Object</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode.html
index 5ad9217ca..b22996eb9 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1SearchStrategyNode.html
@@ -105,9 +105,9 @@ Public Member Functions</h2></td></tr>
<tr class="memitem:a7c01ca65b893757d49b7dca196c0d854"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a7c01c [...]
<tr class="memdesc:a7c01ca65b893757d49b7dca196c0d854"><td class="mdescLeft"> </td><td class="mdescRight">Generate measure candidates from design spaces for measurement. <a href="#a7c01ca65b893757d49b7dca196c0d854">More...</a><br /></td></tr>
<tr class="separator:a7c01ca65b893757d49b7dca196c0d854"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a609a8697917c6041af77478c8f4ef34c"><td class="memItemLeft" align="right" valign="top">virtual void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a609a8697917c6041af77478c8f4ef34c">NotifyRunnerResults</a> (const <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContext.html">TuneContext</a> &context, const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class=" [...]
-<tr class="memdesc:a609a8697917c6041af77478c8f4ef34c"><td class="mdescLeft"> </td><td class="mdescRight">Update the search strategy with measurement results. <a href="#a609a8697917c6041af77478c8f4ef34c">More...</a><br /></td></tr>
-<tr class="separator:a609a8697917c6041af77478c8f4ef34c"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a1a5a62e39bbe941f13ec784b43d7e169"><td class="memItemLeft" align="right" valign="top">virtual void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a1a5a62e39bbe941f13ec784b43d7e169">NotifyRunnerResults</a> (const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > &measure_ca [...]
+<tr class="memdesc:a1a5a62e39bbe941f13ec784b43d7e169"><td class="mdescLeft"> </td><td class="mdescRight">Update the search strategy with measurement results. <a href="#a1a5a62e39bbe941f13ec784b43d7e169">More...</a><br /></td></tr>
+<tr class="separator:a1a5a62e39bbe941f13ec784b43d7e169"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a314b2e2a54bcc6f2363080687f8ecece"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a314b2e2a54bcc6f2363080687f8ecece">TVM_DECLARE_BASE_OBJECT_INFO</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html">SearchStrategyNode</a>, <a class="el" href="classtvm_1_1runtime_1_1Object.html">Object</a>)</td></tr>
<tr class="separator:a314b2e2a54bcc6f2363080687f8ecece"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="inherit_header pub_methods_classtvm_1_1runtime_1_1Object"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1runtime_1_1Object')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td></tr>
@@ -298,8 +298,8 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="a609a8697917c6041af77478c8f4ef34c"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a609a8697917c6041af77478c8f4ef34c">◆ </a></span>NotifyRunnerResults()</h2>
+<a id="a1a5a62e39bbe941f13ec784b43d7e169"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a1a5a62e39bbe941f13ec784b43d7e169">◆ </a></span>NotifyRunnerResults()</h2>
<div class="memitem">
<div class="memproto">
@@ -310,12 +310,6 @@ Additional Inherited Members</h2></td></tr>
<tr>
<td class="memname">virtual void tvm::meta_schedule::SearchStrategyNode::NotifyRunnerResults </td>
<td>(</td>
- <td class="paramtype">const <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContext.html">TuneContext</a> & </td>
- <td class="paramname"><em>context</em>, </td>
- </tr>
- <tr>
- <td class="paramkey"></td>
- <td></td>
<td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > & </td>
<td class="paramname"><em>measure_candidates</em>, </td>
</tr>
@@ -341,14 +335,13 @@ Additional Inherited Members</h2></td></tr>
<p>Update the search strategy with measurement results. </p>
<dl class="params"><dt>Parameters</dt><dd>
<table class="params">
- <tr><td class="paramname">context</td><td>The tuning context. </td></tr>
<tr><td class="paramname">measure_candidates</td><td>The candidates to be measured. </td></tr>
<tr><td class="paramname">results</td><td>The measurement results from the runner. </td></tr>
</table>
</dd>
</dl>
-<p>Implemented in <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a404a53311309ba8e782a0a0c07e96d19">tvm::meta_schedule::PySearchStrategyNode</a>.</p>
+<p>Implemented in <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a6ae774bd7a6caedf58152c562dae5378">tvm::meta_schedule::PySearchStrategyNode</a>.</p>
</div>
</div>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode-members.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode-members.html
index ab011c16d..48bc8e359 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode-members.html
@@ -69,55 +69,60 @@ $(function() {
<p>This is the complete list of members for <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a>, including all inherited members.</p>
<table class="directory">
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5fbebc47be111ecc1d5869bcc0476e21">_GetOrAllocRuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a14b234a745215da158b2386bbb34bd70">_type_child_slots</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a05ece7bcb6bf73e88765c1f193a489ce">_type_child_slots_can_overflow</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55cb618bd4bbcd49317b35ea8e2996be">_type_final</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a92fe62494027b70af1f7696d611c21b6">_type_has_method_sequal_reduce</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac97054694d03dc5eac58315fb569ef88">_type_has_method_shash_reduce</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a74e9f076b50b8b335b4a321e9b0bf03c">_type_has_method_visit_attrs</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af6aed95d70af7e44ce376a8d7be6c5f1">_type_index</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a2e861f72c090f9b5223b71e40d0a511b">_type_key</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4b1da69a97fb1c10ffc5bd4f8872bb23">builder_results</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a70fb5361147634605d6595bb89381f03">DecRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af4407d2b59132e803ff791482dbe0145">deleter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a9e84841ca982bff376a978ade0132631">FDeleter</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a726972ff315c446192df94027ddea032">GetOrAllocRuntimeTypeIndex</a>(const std::string &key, uint32_t static_tindex, uint32_t parent_tindex, uint32_t type_child_slots, bool type_child_slots_can_overflow)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4d951e51832081b85875669eac90e940">GetTypeKey</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5693cbadcc1168b96db7b1cc5c200b86">GetTypeKeyHash</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a8116d7f8fe4aa655e77b481a924a3691">Initialize</a>()</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#abc52e43954ee5c00fc3e8197b5e697b4">is_terminated</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4ede62a091db49ae8e67d84cfba1e859">logging_func</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a85697ab529d4e1aab8b76f051544c638">measure_candidates</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a5c6379933c2e480d775bdc091a666abf">mod</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a66e09f19c74eb8a326455c0a656560f9">mutator_probs</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#aa7136d896f4145357ebb1b7639a25d65">num_threads</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a133436a9ec5c4a768b94102bf95a660b">Object</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#adacb2fc2614c48ad00d23aa93aab4301">postprocs</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#abd83e6598eeb8d3b4b899907e9cf506c">rand_state</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a0d492efee331e2239a093f4b2017c10f">ref_counter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a8b7bfb296b89ad8645fcf89bf645092a">runner_futures</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#ab320bd3e0fd2c2961e1f06c184d183d8">sch_rules</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#ac0030a1f3321be5cbc75226be5690b4b">search_strategy</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a7bdfdd48530bfe380c5f6c143158a07f">space_generator</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#ae2a4edfbc9e6246748fd0e10202cdb66">target</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a5cd36a027a0a4b1840bf3884948c6298">task_name</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a89500f25fff207d09a8f3841453d2153">TVM_DECLARE_FINAL_OBJECT_INFO</a>(TuneContextNode, Object)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a481f01923b14e1851ebd38506e9c66ea">type_index</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4bfc2586cb55f2af47728187b3256255">type_index_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">TypeIndex2Key</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6ee32a02dd44257da105fbbe5d9c8622">TypeIndex2KeyHash</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6841f97e06e6614dd7e82c6dd41b818a">TypeKey2Index</a>(const std::string &key)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a0feacb165880521b85b82f6b4e6f4a8f">VisitAttrs</a>(tvm::AttrVisitor *v)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a346cd319a6d696813eff582128efe2cb">_ClearMeasureState</a>()</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5fbebc47be111ecc1d5869bcc0476e21">_GetOrAllocRuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a9ba45997fc3c6aa97a351fa1944cb109">_Join</a>()</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#aaf53f237cf6958f2e22c3e6dafa68fa0">_SendToBuilder</a>(const Builder &builder)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4acf21616576112d682bd949ce3e52b9">_SendToRunner</a>(const Runner &runner)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#acd048bfe66a01d00f1af3f69e8ec0881">_SetMeasureCandidates</a>(const Array< MeasureCandidate > &candidates)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a14b234a745215da158b2386bbb34bd70">_type_child_slots</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a05ece7bcb6bf73e88765c1f193a489ce">_type_child_slots_can_overflow</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55cb618bd4bbcd49317b35ea8e2996be">_type_final</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a92fe62494027b70af1f7696d611c21b6">_type_has_method_sequal_reduce</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac97054694d03dc5eac58315fb569ef88">_type_has_method_shash_reduce</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a74e9f076b50b8b335b4a321e9b0bf03c">_type_has_method_visit_attrs</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af6aed95d70af7e44ce376a8d7be6c5f1">_type_index</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a2e861f72c090f9b5223b71e40d0a511b">_type_key</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4b1da69a97fb1c10ffc5bd4f8872bb23">builder_results</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a70fb5361147634605d6595bb89381f03">DecRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af4407d2b59132e803ff791482dbe0145">deleter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a9e84841ca982bff376a978ade0132631">FDeleter</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a726972ff315c446192df94027ddea032">GetOrAllocRuntimeTypeIndex</a>(const std::string &key, uint32_t static_tindex, uint32_t parent_tindex, uint32_t type_child_slots, bool type_child_slots_can_overflow)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">static</span [...]
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4d951e51832081b85875669eac90e940">GetTypeKey</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5693cbadcc1168b96db7b1cc5c200b86">GetTypeKeyHash</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a8116d7f8fe4aa655e77b481a924a3691">Initialize</a>()</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#abc52e43954ee5c00fc3e8197b5e697b4">is_terminated</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4ede62a091db49ae8e67d84cfba1e859">logging_func</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a85697ab529d4e1aab8b76f051544c638">measure_candidates</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a5c6379933c2e480d775bdc091a666abf">mod</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a66e09f19c74eb8a326455c0a656560f9">mutator_probs</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#aa7136d896f4145357ebb1b7639a25d65">num_threads</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a133436a9ec5c4a768b94102bf95a660b">Object</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#adacb2fc2614c48ad00d23aa93aab4301">postprocs</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#abd83e6598eeb8d3b4b899907e9cf506c">rand_state</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a0d492efee331e2239a093f4b2017c10f">ref_counter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a8b7bfb296b89ad8645fcf89bf645092a">runner_futures</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#ab320bd3e0fd2c2961e1f06c184d183d8">sch_rules</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#ac0030a1f3321be5cbc75226be5690b4b">search_strategy</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a7bdfdd48530bfe380c5f6c143158a07f">space_generator</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#ae2a4edfbc9e6246748fd0e10202cdb66">target</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a5cd36a027a0a4b1840bf3884948c6298">task_name</a></td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a89500f25fff207d09a8f3841453d2153">TVM_DECLARE_FINAL_OBJECT_INFO</a>(TuneContextNode, Object)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a481f01923b14e1851ebd38506e9c66ea">type_index</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4bfc2586cb55f2af47728187b3256255">type_index_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">TypeIndex2Key</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6ee32a02dd44257da105fbbe5d9c8622">TypeIndex2KeyHash</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6841f97e06e6614dd7e82c6dd41b818a">TypeKey2Index</a>(const std::string &key)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a0feacb165880521b85b82f6b4e6f4a8f">VisitAttrs</a>(tvm::AttrVisitor *v)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">tvm::meta_schedule::TuneContextNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
</table></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode.html
index 099631589..731b2234a 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode.html
@@ -79,13 +79,13 @@ $(function() {
<div class="dynheader">
Inheritance diagram for tvm::meta_schedule::TuneContextNode:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1TuneContextNode__inherit__graph.svg" width="290" height="932"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1TuneContextNode__inherit__graph.svg" width="290" height="1006"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<div class="dynheader">
Collaboration diagram for tvm::meta_schedule::TuneContextNode:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1TuneContextNode__coll__graph.svg" width="3186" height="1404"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1TuneContextNode__coll__graph.svg" width="3186" height="1478"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<table class="memberdecls">
@@ -96,6 +96,21 @@ Public Member Functions</h2></td></tr>
<tr class="memitem:a8116d7f8fe4aa655e77b481a924a3691"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a8116d7f8fe4aa655e77b481a924a3691">Initialize</a> ()</td></tr>
<tr class="memdesc:a8116d7f8fe4aa655e77b481a924a3691"><td class="mdescLeft"> </td><td class="mdescRight">Initialize members that needs initialization with tune context. <a href="#a8116d7f8fe4aa655e77b481a924a3691">More...</a><br /></td></tr>
<tr class="separator:a8116d7f8fe4aa655e77b481a924a3691"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:acd048bfe66a01d00f1af3f69e8ec0881"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#acd048bfe66a01d00f1af3f69e8ec0881">_SetMeasureCandidates</a> (const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > &candidates)</td></tr>
+<tr class="memdesc:acd048bfe66a01d00f1af3f69e8ec0881"><td class="mdescLeft"> </td><td class="mdescRight">Set the measure candidates from the <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html" title="Managed reference to SearchStrategyNode. ">SearchStrategy</a>. <a href="#acd048bfe66a01d00f1af3f69e8ec0881">More...</a><br /></td></tr>
+<tr class="separator:acd048bfe66a01d00f1af3f69e8ec0881"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aaf53f237cf6958f2e22c3e6dafa68fa0"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#aaf53f237cf6958f2e22c3e6dafa68fa0">_SendToBuilder</a> (const <a class="el" href="classtvm_1_1meta__schedule_1_1Builder.html">Builder</a> &builder)</td></tr>
+<tr class="memdesc:aaf53f237cf6958f2e22c3e6dafa68fa0"><td class="mdescLeft"> </td><td class="mdescRight">Send the measure candidates to builder. <a href="#aaf53f237cf6958f2e22c3e6dafa68fa0">More...</a><br /></td></tr>
+<tr class="separator:aaf53f237cf6958f2e22c3e6dafa68fa0"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a4acf21616576112d682bd949ce3e52b9"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4acf21616576112d682bd949ce3e52b9">_SendToRunner</a> (const <a class="el" href="classtvm_1_1meta__schedule_1_1Runner.html">Runner</a> &runner)</td></tr>
+<tr class="memdesc:a4acf21616576112d682bd949ce3e52b9"><td class="mdescLeft"> </td><td class="mdescRight">Send the built measure candidates to runner. <a href="#a4acf21616576112d682bd949ce3e52b9">More...</a><br /></td></tr>
+<tr class="separator:a4acf21616576112d682bd949ce3e52b9"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a9ba45997fc3c6aa97a351fa1944cb109"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1RunnerResult.html">RunnerResult</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a9ba45997fc3c6aa97a351fa1944cb109">_Join</a> ()</td></tr>
+<tr class="memdesc:a9ba45997fc3c6aa97a351fa1944cb109"><td class="mdescLeft"> </td><td class="mdescRight">Join the running tasks. <a href="#a9ba45997fc3c6aa97a351fa1944cb109">More...</a><br /></td></tr>
+<tr class="separator:a9ba45997fc3c6aa97a351fa1944cb109"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a346cd319a6d696813eff582128efe2cb"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a346cd319a6d696813eff582128efe2cb">_ClearMeasureState</a> ()</td></tr>
+<tr class="memdesc:a346cd319a6d696813eff582128efe2cb"><td class="mdescLeft"> </td><td class="mdescRight">Set <code>measure_candidates</code>, <code>builder_results</code> and <code>runner_futures</code> to null. <a href="#a346cd319a6d696813eff582128efe2cb">More...</a><br /></td></tr>
+<tr class="separator:a346cd319a6d696813eff582128efe2cb"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a89500f25fff207d09a8f3841453d2153"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a89500f25fff207d09a8f3841453d2153">TVM_DECLARE_FINAL_OBJECT_INFO</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html">TuneContextNode</a>, <a class="el" href="classtvm_1_1runtime_1_1Object.html">Object</a>)</td></tr>
<tr class="separator:a89500f25fff207d09a8f3841453d2153"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="inherit_header pub_methods_classtvm_1_1runtime_1_1Object"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1runtime_1_1Object')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td></tr>
@@ -238,6 +253,117 @@ Additional Inherited Members</h2></td></tr>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
<div class="textblock"><p>The auto tuning context. </p>
</div><h2 class="groupheader">Member Function Documentation</h2>
+<a id="a346cd319a6d696813eff582128efe2cb"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a346cd319a6d696813eff582128efe2cb">◆ </a></span>_ClearMeasureState()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::meta_schedule::TuneContextNode::_ClearMeasureState </td>
+ <td>(</td>
+ <td class="paramname"></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Set <code>measure_candidates</code>, <code>builder_results</code> and <code>runner_futures</code> to null. </p>
+
+</div>
+</div>
+<a id="a9ba45997fc3c6aa97a351fa1944cb109"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a9ba45997fc3c6aa97a351fa1944cb109">◆ </a></span>_Join()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname"><a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a><<a class="el" href="classtvm_1_1meta__schedule_1_1RunnerResult.html">RunnerResult</a>> tvm::meta_schedule::TuneContextNode::_Join </td>
+ <td>(</td>
+ <td class="paramname"></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Join the running tasks. </p>
+<dl class="section return"><dt>Returns</dt><dd>The results from the runner </dd></dl>
+
+</div>
+</div>
+<a id="aaf53f237cf6958f2e22c3e6dafa68fa0"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#aaf53f237cf6958f2e22c3e6dafa68fa0">◆ </a></span>_SendToBuilder()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::meta_schedule::TuneContextNode::_SendToBuilder </td>
+ <td>(</td>
+ <td class="paramtype">const <a class="el" href="classtvm_1_1meta__schedule_1_1Builder.html">Builder</a> & </td>
+ <td class="paramname"><em>builder</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Send the measure candidates to builder. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">builder</td><td>The builder to send the candidates to. </td></tr>
+ </table>
+ </dd>
+</dl>
+
+</div>
+</div>
+<a id="a4acf21616576112d682bd949ce3e52b9"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a4acf21616576112d682bd949ce3e52b9">◆ </a></span>_SendToRunner()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::meta_schedule::TuneContextNode::_SendToRunner </td>
+ <td>(</td>
+ <td class="paramtype">const <a class="el" href="classtvm_1_1meta__schedule_1_1Runner.html">Runner</a> & </td>
+ <td class="paramname"><em>runner</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Send the built measure candidates to runner. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">runner</td><td>The runner to send the candidates to. </td></tr>
+ </table>
+ </dd>
+</dl>
+
+</div>
+</div>
+<a id="acd048bfe66a01d00f1af3f69e8ec0881"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#acd048bfe66a01d00f1af3f69e8ec0881">◆ </a></span>_SetMeasureCandidates()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void tvm::meta_schedule::TuneContextNode::_SetMeasureCandidates </td>
+ <td>(</td>
+ <td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1MeasureCandidate.html">MeasureCandidate</a> > & </td>
+ <td class="paramname"><em>candidates</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Set the measure candidates from the <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategy.html" title="Managed reference to SearchStrategyNode. ">SearchStrategy</a>. </p>
+
+</div>
+</div>
<a id="a8116d7f8fe4aa655e77b481a924a3691"></a>
<h2 class="memtitle"><span class="permalink"><a href="#a8116d7f8fe4aa655e77b481a924a3691">◆ </a></span>Initialize()</h2>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__coll__graph.svg
index 18915e17f..0666ff6f7 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__coll__graph.svg
@@ -4,589 +4,594 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::meta_schedule::TuneContextNode Pages: 1 -->
-<svg width="2389pt" height="1053pt"
- viewBox="0.00 0.00 2389.00 1053.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1049)">
+<svg width="2389pt" height="1108pt"
+ viewBox="0.00 0.00 2389.00 1108.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1104)">
<title>tvm::meta_schedule::TuneContextNode</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1049 2385,-1049 2385,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1104 2385,-1104 2385,4 -4,4"/>
<!-- Node2 -->
<g id="node1" class="node">
<title>Node2</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="1216,-.5 1216,-123.5 1425,-123.5 1425,-.5 1216,-.5"/>
-<text text-anchor="start" x="1224" y="-111.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
-<text text-anchor="middle" x="1320.5" y="-100.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::TuneContextNode</text>
-<polyline fill="none" stroke="#000000" points="1216,-93.5 1425,-93.5 "/>
-<text text-anchor="start" x="1224" y="-81.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ rand_state</text>
-<text text-anchor="start" x="1224" y="-70.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ num_threads</text>
-<text text-anchor="start" x="1224" y="-59.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_terminated</text>
-<text text-anchor="start" x="1224" y="-48.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<polyline fill="none" stroke="#000000" points="1216,-41.5 1425,-41.5 "/>
-<text text-anchor="start" x="1224" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
-<text text-anchor="start" x="1224" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Initialize()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="1216,-.5 1216,-178.5 1425,-178.5 1425,-.5 1216,-.5"/>
+<text text-anchor="start" x="1224" y="-166.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
+<text text-anchor="middle" x="1320.5" y="-155.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::TuneContextNode</text>
+<polyline fill="none" stroke="#000000" points="1216,-148.5 1425,-148.5 "/>
+<text text-anchor="start" x="1224" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ rand_state</text>
+<text text-anchor="start" x="1224" y="-125.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ num_threads</text>
+<text text-anchor="start" x="1224" y="-114.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_terminated</text>
+<text text-anchor="start" x="1224" y="-103.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<polyline fill="none" stroke="#000000" points="1216,-96.5 1425,-96.5 "/>
+<text text-anchor="start" x="1224" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
+<text text-anchor="start" x="1224" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Initialize()</text>
+<text text-anchor="start" x="1224" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _SetMeasureCandidates()</text>
+<text text-anchor="start" x="1224" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _SendToBuilder()</text>
+<text text-anchor="start" x="1224" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _SendToRunner()</text>
+<text text-anchor="start" x="1224" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _Join()</text>
+<text text-anchor="start" x="1224" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _ClearMeasureState()</text>
<text text-anchor="start" x="1224" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
</g>
<!-- Node3 -->
<g id="node2" class="node">
<title>Node3</title>
<g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1Object.html" target="_top" xlink:title="base class of all object containers. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-171.5 0,-558.5 183,-558.5 183,-171.5 0,-171.5"/>
-<text text-anchor="middle" x="91.5" y="-546.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
-<polyline fill="none" stroke="#000000" points="0,-539.5 183,-539.5 "/>
-<text text-anchor="start" x="8" y="-527.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="8" y="-516.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
-<text text-anchor="start" x="8" y="-505.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
-<text text-anchor="start" x="8" y="-494.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
-<text text-anchor="start" x="8" y="-483.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
-<text text-anchor="start" x="8" y="-472.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
-<text text-anchor="start" x="8" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
-<text text-anchor="start" x="8" y="-450.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="8" y="-439.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="8" y="-428.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
-<text text-anchor="start" x="8" y="-417.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="8" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="8" y="-395.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
-<text text-anchor="start" x="8" y="-384.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
-<polyline fill="none" stroke="#000000" points="0,-377.5 183,-377.5 "/>
-<text text-anchor="start" x="8" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
-<text text-anchor="start" x="8" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
-<text text-anchor="start" x="8" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
-<text text-anchor="start" x="8" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
-<text text-anchor="start" x="8" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="8" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="8" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="8" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="8" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="8" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="8" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
-<text text-anchor="start" x="8" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
-<text text-anchor="start" x="8" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
-<text text-anchor="start" x="8" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
-<text text-anchor="start" x="8" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
-<text text-anchor="start" x="8" y="-200.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
-<text text-anchor="start" x="8" y="-189.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
-<text text-anchor="start" x="8" y="-178.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
+<polygon fill="#ffffff" stroke="#000000" points="0,-226.5 0,-613.5 183,-613.5 183,-226.5 0,-226.5"/>
+<text text-anchor="middle" x="91.5" y="-601.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="0,-594.5 183,-594.5 "/>
+<text text-anchor="start" x="8" y="-582.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="8" y="-571.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="8" y="-560.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="8" y="-549.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="8" y="-538.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="8" y="-527.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="8" y="-516.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="8" y="-505.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="8" y="-494.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="8" y="-483.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="8" y="-472.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="8" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="8" y="-450.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="8" y="-439.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<polyline fill="none" stroke="#000000" points="0,-432.5 183,-432.5 "/>
+<text text-anchor="start" x="8" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="8" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="8" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="8" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="8" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="8" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="8" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="8" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="8" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="8" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="8" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="8" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="8" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="8" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="8" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="8" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="8" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="8" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
</a>
</g>
</g>
<!-- Node3->Node2 -->
<g id="edge1" class="edge">
<title>Node3->Node2</title>
-<path fill="none" stroke="#191970" d="M190.5277,-227.6767C211.9807,-205.769 236.212,-185.5604 262.5,-171 344.6786,-125.483 964.7571,-83.4537 1215.63,-68.1295"/>
-<polygon fill="none" stroke="#191970" points="187.7459,-225.5214 183.36,-235.1658 192.8029,-230.3615 187.7459,-225.5214"/>
+<path fill="none" stroke="#191970" d="M190.5277,-282.6767C211.9807,-260.769 236.212,-240.5604 262.5,-226 424.9167,-136.0407 981.9076,-103.2641 1215.7817,-93.2806"/>
+<polygon fill="none" stroke="#191970" points="187.7459,-280.5214 183.36,-290.1658 192.8029,-285.3615 187.7459,-280.5214"/>
</g>
<!-- Node3->Node3 -->
<g id="edge2" class="edge">
<title>Node3->Node3</title>
-<path fill="none" stroke="#404040" d="M183.3625,-398.9248C194.0482,-392.6637 201,-381.3555 201,-365 201,-354.0112 197.8618,-345.3007 192.5615,-338.8687"/>
-<polygon fill="none" stroke="#404040" points="192.5184,-338.8322 185.3548,-338.0056 183.3625,-331.0752 190.5261,-331.9017 192.5184,-338.8322"/>
-<text text-anchor="middle" x="227" y="-362.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #deleter_</text>
+<path fill="none" stroke="#404040" d="M183.3625,-453.9248C194.0482,-447.6637 201,-436.3555 201,-420 201,-409.0112 197.8618,-400.3007 192.5615,-393.8687"/>
+<polygon fill="none" stroke="#404040" points="192.5184,-393.8322 185.3548,-393.0056 183.3625,-386.0752 190.5261,-386.9017 192.5184,-393.8322"/>
+<text text-anchor="middle" x="227" y="-417.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #deleter_</text>
</g>
<!-- Node4 -->
<g id="node3" class="node">
<title>Node4</title>
<g id="a_node3"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::meta_schedule::\lSearchStrategy \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="271.5,-270.5 271.5,-459.5 405.5,-459.5 405.5,-270.5 271.5,-270.5"/>
-<text text-anchor="start" x="279.5" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="start" x="279.5" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::</text>
-<text text-anchor="middle" x="338.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">SearchStrategy ></text>
-<polyline fill="none" stroke="#000000" points="271.5,-418.5 405.5,-418.5 "/>
-<text text-anchor="start" x="279.5" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="271.5,-399.5 405.5,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="271.5,-325.5 271.5,-514.5 405.5,-514.5 405.5,-325.5 271.5,-325.5"/>
+<text text-anchor="start" x="279.5" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="start" x="279.5" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::</text>
+<text text-anchor="middle" x="338.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">SearchStrategy ></text>
+<polyline fill="none" stroke="#000000" points="271.5,-473.5 405.5,-473.5 "/>
+<text text-anchor="start" x="279.5" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="271.5,-454.5 405.5,-454.5 "/>
+<text text-anchor="start" x="279.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="279.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="279.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="279.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="279.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="279.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="279.5" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="279.5" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="279.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="279.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="279.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="279.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="279.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="279.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="279.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="279.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="279.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="279.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="279.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node4->Node2 -->
<g id="edge3" class="edge">
<title>Node4->Node2</title>
-<path fill="none" stroke="#404040" d="M357.5637,-270.4336C368.8878,-235.203 386.6965,-197.4039 414.5,-171 444.0547,-142.933 461.6334,-150.479 501.5,-142 748.0051,-89.5725 1043.673,-71.412 1203.7016,-65.1873"/>
-<polygon fill="none" stroke="#404040" points="1203.938,-65.1784 1209.7824,-60.9544 1215.9294,-64.7247 1210.0849,-68.9487 1203.938,-65.1784"/>
-<text text-anchor="middle" x="546.5" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +search_strategy</text>
+<path fill="none" stroke="#404040" d="M357.5637,-325.4336C368.8878,-290.203 386.6965,-252.4039 414.5,-226 444.0547,-197.933 461.7794,-206.1384 501.5,-197 748.0358,-140.2805 1043.6922,-110.6852 1203.7105,-97.7648"/>
+<polygon fill="none" stroke="#404040" points="1203.9756,-97.7437 1209.6382,-93.2789 1215.9375,-96.7888 1210.2749,-101.2536 1203.9756,-97.7437"/>
+<text text-anchor="middle" x="546.5" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +search_strategy</text>
</g>
<!-- Node5 -->
<g id="node4" class="node">
<title>Node5</title>
<g id="a_node4"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="1328.5,-596.5 1328.5,-818.5 1462.5,-818.5 1462.5,-596.5 1328.5,-596.5"/>
-<text text-anchor="middle" x="1395.5" y="-806.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="1328.5,-799.5 1462.5,-799.5 "/>
-<text text-anchor="start" x="1336.5" y="-787.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="1328.5,-780.5 1462.5,-780.5 "/>
-<text text-anchor="start" x="1336.5" y="-768.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="1336.5" y="-757.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="1336.5" y="-746.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="1336.5" y="-735.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="1336.5" y="-724.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="1336.5" y="-713.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
-<text text-anchor="start" x="1336.5" y="-702.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="1336.5" y="-691.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="1336.5" y="-680.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="1336.5" y="-669.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="1336.5" y="-658.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="1336.5" y="-647.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="1336.5" y="-636.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="1336.5" y="-625.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="1336.5" y="-614.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="1336.5" y="-603.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<polygon fill="#ffffff" stroke="#000000" points="1328.5,-651.5 1328.5,-873.5 1462.5,-873.5 1462.5,-651.5 1328.5,-651.5"/>
+<text text-anchor="middle" x="1395.5" y="-861.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="1328.5,-854.5 1462.5,-854.5 "/>
+<text text-anchor="start" x="1336.5" y="-842.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="1328.5,-835.5 1462.5,-835.5 "/>
+<text text-anchor="start" x="1336.5" y="-823.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="1336.5" y="-812.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="1336.5" y="-801.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="1336.5" y="-790.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="1336.5" y="-779.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="1336.5" y="-768.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
+<text text-anchor="start" x="1336.5" y="-757.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="1336.5" y="-746.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="1336.5" y="-735.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="1336.5" y="-724.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="1336.5" y="-713.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="1336.5" y="-702.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="1336.5" y="-691.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="1336.5" y="-680.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="1336.5" y="-669.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="1336.5" y="-658.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
</a>
</g>
</g>
<!-- Node5->Node4 -->
<g id="edge4" class="edge">
<title>Node5->Node4</title>
-<path fill="none" stroke="#191970" d="M1318.2386,-705.5367C1111.903,-698.8147 554.1507,-670.5116 414.5,-559 383.8305,-534.5103 365.5063,-495.9311 354.5719,-459.6047"/>
-<polygon fill="none" stroke="#191970" points="1318.2783,-709.0396 1328.3844,-705.8589 1318.5006,-702.0431 1318.2783,-709.0396"/>
+<path fill="none" stroke="#191970" d="M1318.2386,-760.5367C1111.903,-753.8147 554.1507,-725.5116 414.5,-614 383.8305,-589.5103 365.5063,-550.9311 354.5719,-514.6047"/>
+<polygon fill="none" stroke="#191970" points="1318.2783,-764.0396 1328.3844,-760.8589 1318.5006,-757.0431 1318.2783,-764.0396"/>
</g>
<!-- Node7 -->
<g id="node6" class="node">
<title>Node7</title>
<g id="a_node6"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::meta_schedule::\lSpaceGenerator \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="423.5,-270.5 423.5,-459.5 557.5,-459.5 557.5,-270.5 423.5,-270.5"/>
-<text text-anchor="start" x="431.5" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="start" x="431.5" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::</text>
-<text text-anchor="middle" x="490.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">SpaceGenerator ></text>
-<polyline fill="none" stroke="#000000" points="423.5,-418.5 557.5,-418.5 "/>
-<text text-anchor="start" x="431.5" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="423.5,-399.5 557.5,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="423.5,-325.5 423.5,-514.5 557.5,-514.5 557.5,-325.5 423.5,-325.5"/>
+<text text-anchor="start" x="431.5" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="start" x="431.5" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::</text>
+<text text-anchor="middle" x="490.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">SpaceGenerator ></text>
+<polyline fill="none" stroke="#000000" points="423.5,-473.5 557.5,-473.5 "/>
+<text text-anchor="start" x="431.5" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="423.5,-454.5 557.5,-454.5 "/>
+<text text-anchor="start" x="431.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="431.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="431.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="431.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="431.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="431.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="431.5" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="431.5" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="431.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="431.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="431.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="431.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="431.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="431.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="431.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="431.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="431.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="431.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="431.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node5->Node7 -->
<g id="edge7" class="edge">
<title>Node5->Node7</title>
-<path fill="none" stroke="#191970" d="M1318.1318,-703.1334C1134.8864,-691.3331 681.1614,-653.1218 566.5,-559 536.3039,-534.213 518.0593,-495.8122 507.0565,-459.6958"/>
-<polygon fill="none" stroke="#191970" points="1318.029,-706.6338 1328.2307,-703.7745 1318.4726,-699.6479 1318.029,-706.6338"/>
+<path fill="none" stroke="#191970" d="M1318.1318,-758.1334C1134.8864,-746.3331 681.1614,-708.1218 566.5,-614 536.3039,-589.213 518.0593,-550.8122 507.0565,-514.6958"/>
+<polygon fill="none" stroke="#191970" points="1318.029,-761.6338 1328.2307,-758.7745 1318.4726,-754.6479 1318.029,-761.6338"/>
</g>
<!-- Node8 -->
<g id="node7" class="node">
<title>Node8</title>
<g id="a_node7"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::runtime::Array\l\< tvm::meta_schedule::RunnerFuture \> \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="575.5,-270.5 575.5,-459.5 795.5,-459.5 795.5,-270.5 575.5,-270.5"/>
-<text text-anchor="start" x="583.5" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="start" x="583.5" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Array</text>
-<text text-anchor="middle" x="685.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::RunnerFuture > ></text>
-<polyline fill="none" stroke="#000000" points="575.5,-418.5 795.5,-418.5 "/>
-<text text-anchor="start" x="583.5" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="575.5,-399.5 795.5,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="575.5,-325.5 575.5,-514.5 795.5,-514.5 795.5,-325.5 575.5,-325.5"/>
+<text text-anchor="start" x="583.5" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="start" x="583.5" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Array</text>
+<text text-anchor="middle" x="685.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::RunnerFuture > ></text>
+<polyline fill="none" stroke="#000000" points="575.5,-473.5 795.5,-473.5 "/>
+<text text-anchor="start" x="583.5" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="575.5,-454.5 795.5,-454.5 "/>
+<text text-anchor="start" x="583.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="583.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="583.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="583.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="583.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="583.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="583.5" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="583.5" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="583.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="583.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="583.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="583.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="583.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="583.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="583.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="583.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="583.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="583.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="583.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node5->Node8 -->
<g id="edge9" class="edge">
<title>Node5->Node8</title>
-<path fill="none" stroke="#191970" d="M1318.1196,-695.5047C1177.3362,-672.4892 886.2875,-619.0565 804.5,-559 770.2633,-533.86 743.7963,-495.6249 724.6108,-459.7254"/>
-<polygon fill="none" stroke="#191970" points="1317.9691,-699.0261 1328.401,-697.1751 1319.0917,-692.1167 1317.9691,-699.0261"/>
+<path fill="none" stroke="#191970" d="M1318.1196,-750.5047C1177.3362,-727.4892 886.2875,-674.0565 804.5,-614 770.2633,-588.86 743.7963,-550.6249 724.6108,-514.7254"/>
+<polygon fill="none" stroke="#191970" points="1317.9691,-754.0261 1328.401,-752.1751 1319.0917,-747.1167 1317.9691,-754.0261"/>
</g>
<!-- Node9 -->
<g id="node8" class="node">
<title>Node9</title>
<g id="a_node8"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::runtime::Array\l\< tvm::meta_schedule::MeasureCandidate \> \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="814,-270.5 814,-459.5 1061,-459.5 1061,-270.5 814,-270.5"/>
-<text text-anchor="start" x="822" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="start" x="822" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Array</text>
-<text text-anchor="middle" x="937.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::MeasureCandidate > ></text>
-<polyline fill="none" stroke="#000000" points="814,-418.5 1061,-418.5 "/>
-<text text-anchor="start" x="822" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="814,-399.5 1061,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="814,-325.5 814,-514.5 1061,-514.5 1061,-325.5 814,-325.5"/>
+<text text-anchor="start" x="822" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="start" x="822" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Array</text>
+<text text-anchor="middle" x="937.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::MeasureCandidate > ></text>
+<polyline fill="none" stroke="#000000" points="814,-473.5 1061,-473.5 "/>
+<text text-anchor="start" x="822" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="814,-454.5 1061,-454.5 "/>
+<text text-anchor="start" x="822" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="822" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="822" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="822" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="822" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="822" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="822" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="822" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="822" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="822" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="822" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="822" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="822" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="822" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="822" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="822" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="822" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="822" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="822" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node5->Node9 -->
<g id="edge11" class="edge">
<title>Node5->Node9</title>
-<path fill="none" stroke="#191970" d="M1318.6145,-685.4883C1248.2979,-662.5049 1144.2998,-621.061 1070.5,-559 1037.8401,-531.535 1009.6821,-494.1664 987.7929,-459.5561"/>
-<polygon fill="none" stroke="#191970" points="1317.7148,-688.8756 1328.3063,-688.6091 1319.8604,-682.2125 1317.7148,-688.8756"/>
+<path fill="none" stroke="#191970" d="M1318.6145,-740.4883C1248.2979,-717.5049 1144.2998,-676.061 1070.5,-614 1037.8401,-586.535 1009.6821,-549.1664 987.7929,-514.5561"/>
+<polygon fill="none" stroke="#191970" points="1317.7148,-743.8756 1328.3063,-743.6091 1319.8604,-737.2125 1317.7148,-743.8756"/>
</g>
<!-- Node10 -->
<g id="node9" class="node">
<title>Node10</title>
<g id="a_node9"><a xlink:href="classtvm_1_1runtime_1_1PackedFunc.html" target="_top" xlink:title="Packed function is a type-erased function. The arguments are passed by packed format. ">
-<polygon fill="#ffffff" stroke="#000000" points="1079.5,-298 1079.5,-432 1233.5,-432 1233.5,-298 1079.5,-298"/>
-<text text-anchor="middle" x="1156.5" y="-420" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::PackedFunc</text>
-<polyline fill="none" stroke="#000000" points="1079.5,-413 1233.5,-413 "/>
-<text text-anchor="middle" x="1156.5" y="-401" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="1079.5,-394 1233.5,-394 "/>
-<text text-anchor="start" x="1087.5" y="-382" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PackedFunc()</text>
-<text text-anchor="start" x="1087.5" y="-371" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PackedFunc()</text>
-<text text-anchor="start" x="1087.5" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator()()</text>
-<text text-anchor="start" x="1087.5" y="-349" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ CallPacked()</text>
-<text text-anchor="start" x="1087.5" y="-338" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="1087.5" y="-327" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="1087.5" y="-316" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="1087.5" y="-305" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<polygon fill="#ffffff" stroke="#000000" points="1079.5,-353 1079.5,-487 1233.5,-487 1233.5,-353 1079.5,-353"/>
+<text text-anchor="middle" x="1156.5" y="-475" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::PackedFunc</text>
+<polyline fill="none" stroke="#000000" points="1079.5,-468 1233.5,-468 "/>
+<text text-anchor="middle" x="1156.5" y="-456" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="1079.5,-449 1233.5,-449 "/>
+<text text-anchor="start" x="1087.5" y="-437" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PackedFunc()</text>
+<text text-anchor="start" x="1087.5" y="-426" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PackedFunc()</text>
+<text text-anchor="start" x="1087.5" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator()()</text>
+<text text-anchor="start" x="1087.5" y="-404" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ CallPacked()</text>
+<text text-anchor="start" x="1087.5" y="-393" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="1087.5" y="-382" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="1087.5" y="-371" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="1087.5" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
</a>
</g>
</g>
<!-- Node5->Node10 -->
<g id="edge13" class="edge">
<title>Node5->Node10</title>
-<path fill="none" stroke="#191970" d="M1320.6902,-645.0434C1294.006,-620.1881 1265.2114,-590.1102 1243.5,-559 1216.249,-519.952 1194.3707,-470.9963 1179.3701,-432.0331"/>
-<polygon fill="none" stroke="#191970" points="1318.4247,-647.7151 1328.1529,-651.9119 1323.1652,-642.5645 1318.4247,-647.7151"/>
+<path fill="none" stroke="#191970" d="M1320.6902,-700.0434C1294.006,-675.1881 1265.2114,-645.1102 1243.5,-614 1216.249,-574.952 1194.3707,-525.9963 1179.3701,-487.0331"/>
+<polygon fill="none" stroke="#191970" points="1318.4247,-702.7151 1328.1529,-706.9119 1323.1652,-697.5645 1318.4247,-702.7151"/>
</g>
<!-- Node11 -->
<g id="node10" class="node">
<title>Node11</title>
<g id="a_node10"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::runtime::String \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="1252,-276 1252,-454 1389,-454 1389,-276 1252,-276"/>
-<text text-anchor="start" x="1260" y="-442" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="middle" x="1320.5" y="-431" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::String ></text>
-<polyline fill="none" stroke="#000000" points="1252,-424 1389,-424 "/>
-<text text-anchor="start" x="1260" y="-412" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="1252,-405 1389,-405 "/>
+<polygon fill="#ffffff" stroke="#000000" points="1252,-331 1252,-509 1389,-509 1389,-331 1252,-331"/>
+<text text-anchor="start" x="1260" y="-497" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="middle" x="1320.5" y="-486" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::String ></text>
+<polyline fill="none" stroke="#000000" points="1252,-479 1389,-479 "/>
+<text text-anchor="start" x="1260" y="-467" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="1252,-460 1389,-460 "/>
+<text text-anchor="start" x="1260" y="-448" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1260" y="-437" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1260" y="-426" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1260" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1260" y="-404" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="1260" y="-393" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="1260" y="-382" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="1260" y="-371" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1260" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1260" y="-349" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1260" y="-338" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1260" y="-327" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1260" y="-316" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1260" y="-305" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1260" y="-294" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1260" y="-283" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="1260" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1260" y="-349" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1260" y="-338" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node5->Node11 -->
<g id="edge15" class="edge">
<title>Node5->Node11</title>
-<path fill="none" stroke="#191970" d="M1369.0046,-586.5043C1359.4664,-542.9464 1348.886,-494.6293 1340.0472,-454.2656"/>
-<polygon fill="none" stroke="#191970" points="1365.5915,-587.2802 1371.1496,-596.3001 1372.4295,-585.7828 1365.5915,-587.2802"/>
+<path fill="none" stroke="#191970" d="M1369.0046,-641.5043C1359.4664,-597.9464 1348.886,-549.6293 1340.0472,-509.2656"/>
+<polygon fill="none" stroke="#191970" points="1365.5915,-642.2802 1371.1496,-651.3001 1372.4295,-640.7828 1365.5915,-642.2802"/>
</g>
<!-- Node12 -->
<g id="node11" class="node">
<title>Node12</title>
<g id="a_node11"><a xlink:href="classtvm_1_1runtime_1_1Array.html" target="_top" xlink:title="{tvm::runtime::Array\l\< tvm::meta_schedule\l::Postproc \>\n||+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ operator=()\l+ operator=()\land 24 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="1407.5,-270.5 1407.5,-459.5 1535.5,-459.5 1535.5,-270.5 1407.5,-270.5"/>
-<text text-anchor="start" x="1415.5" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Array</text>
-<text text-anchor="start" x="1415.5" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule</text>
-<text text-anchor="middle" x="1471.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Postproc ></text>
-<polyline fill="none" stroke="#000000" points="1407.5,-418.5 1535.5,-418.5 "/>
-<text text-anchor="middle" x="1471.5" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="1407.5,-399.5 1535.5,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="1407.5,-325.5 1407.5,-514.5 1535.5,-514.5 1535.5,-325.5 1407.5,-325.5"/>
+<text text-anchor="start" x="1415.5" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Array</text>
+<text text-anchor="start" x="1415.5" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule</text>
+<text text-anchor="middle" x="1471.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Postproc ></text>
+<polyline fill="none" stroke="#000000" points="1407.5,-473.5 1535.5,-473.5 "/>
+<text text-anchor="middle" x="1471.5" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="1407.5,-454.5 1535.5,-454.5 "/>
+<text text-anchor="start" x="1415.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1415.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1415.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1415.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1415.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
<text text-anchor="start" x="1415.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
<text text-anchor="start" x="1415.5" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
<text text-anchor="start" x="1415.5" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1415.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1415.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1415.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1415.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1415.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1415.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1415.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1415.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 24 more...</text>
+<text text-anchor="start" x="1415.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1415.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1415.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 24 more...</text>
</a>
</g>
</g>
<!-- Node5->Node12 -->
<g id="edge17" class="edge">
<title>Node5->Node12</title>
-<path fill="none" stroke="#191970" d="M1422.3771,-586.3761C1431.6156,-544.742 1441.816,-498.7731 1450.5165,-459.5637"/>
-<polygon fill="none" stroke="#191970" points="1418.9245,-585.7793 1420.175,-596.3001 1425.7583,-587.2957 1418.9245,-585.7793"/>
+<path fill="none" stroke="#191970" d="M1422.3771,-641.3761C1431.6156,-599.742 1441.816,-553.7731 1450.5165,-514.5637"/>
+<polygon fill="none" stroke="#191970" points="1418.9245,-640.7793 1420.175,-651.3001 1425.7583,-642.2957 1418.9245,-640.7793"/>
</g>
<!-- Node13 -->
<g id="node12" class="node">
<title>Node13</title>
<g id="a_node12"><a xlink:href="classtvm_1_1runtime_1_1Map.html" target="_top" xlink:title="{tvm::runtime::Map\<\l tvm::meta_schedule\l::Mutator, tvm::FloatImm \>\n||+ Map()\l+ Map()\l+ Map()\l+ Map()\l+ Map()\l+ Map()\l+ Map()\l+ operator=()\l+ operator=()\l+ at()\land 12 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="1554,-270.5 1554,-459.5 1703,-459.5 1703,-270.5 1554,-270.5"/>
-<text text-anchor="start" x="1562" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Map<</text>
-<text text-anchor="start" x="1562" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> tvm::meta_schedule</text>
-<text text-anchor="middle" x="1628.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Mutator, tvm::FloatImm ></text>
-<polyline fill="none" stroke="#000000" points="1554,-418.5 1703,-418.5 "/>
-<text text-anchor="middle" x="1628.5" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="1554,-399.5 1703,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="1554,-325.5 1554,-514.5 1703,-514.5 1703,-325.5 1554,-325.5"/>
+<text text-anchor="start" x="1562" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Map<</text>
+<text text-anchor="start" x="1562" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> tvm::meta_schedule</text>
+<text text-anchor="middle" x="1628.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Mutator, tvm::FloatImm ></text>
+<polyline fill="none" stroke="#000000" points="1554,-473.5 1703,-473.5 "/>
+<text text-anchor="middle" x="1628.5" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="1554,-454.5 1703,-454.5 "/>
+<text text-anchor="start" x="1562" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
+<text text-anchor="start" x="1562" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
+<text text-anchor="start" x="1562" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
+<text text-anchor="start" x="1562" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
+<text text-anchor="start" x="1562" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
<text text-anchor="start" x="1562" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
<text text-anchor="start" x="1562" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
-<text text-anchor="start" x="1562" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
-<text text-anchor="start" x="1562" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
-<text text-anchor="start" x="1562" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
-<text text-anchor="start" x="1562" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
-<text text-anchor="start" x="1562" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Map()</text>
-<text text-anchor="start" x="1562" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1562" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1562" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ at()</text>
-<text text-anchor="start" x="1562" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
+<text text-anchor="start" x="1562" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1562" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1562" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ at()</text>
+<text text-anchor="start" x="1562" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 12 more...</text>
</a>
</g>
</g>
<!-- Node5->Node13 -->
<g id="edge19" class="edge">
<title>Node5->Node13</title>
-<path fill="none" stroke="#191970" d="M1470.3678,-643.6561C1496.1506,-619.0507 1523.732,-589.497 1544.5,-559 1565.1584,-528.6638 1582.4948,-492.4257 1595.9523,-459.5255"/>
-<polygon fill="none" stroke="#191970" points="1467.6706,-641.3886 1462.7934,-650.7942 1472.4714,-646.483 1467.6706,-641.3886"/>
+<path fill="none" stroke="#191970" d="M1470.3678,-698.6561C1496.1506,-674.0507 1523.732,-644.497 1544.5,-614 1565.1584,-583.6638 1582.4948,-547.4257 1595.9523,-514.5255"/>
+<polygon fill="none" stroke="#191970" points="1467.6706,-696.3886 1462.7934,-705.7942 1472.4714,-701.483 1467.6706,-696.3886"/>
</g>
<!-- Node14 -->
<g id="node13" class="node">
<title>Node14</title>
<g id="a_node13"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::IRModule \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="1721.5,-276 1721.5,-454 1849.5,-454 1849.5,-276 1721.5,-276"/>
-<text text-anchor="start" x="1729.5" y="-442" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="middle" x="1785.5" y="-431" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::IRModule ></text>
-<polyline fill="none" stroke="#000000" points="1721.5,-424 1849.5,-424 "/>
-<text text-anchor="start" x="1729.5" y="-412" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="1721.5,-405 1849.5,-405 "/>
+<polygon fill="#ffffff" stroke="#000000" points="1721.5,-331 1721.5,-509 1849.5,-509 1849.5,-331 1721.5,-331"/>
+<text text-anchor="start" x="1729.5" y="-497" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="middle" x="1785.5" y="-486" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::IRModule ></text>
+<polyline fill="none" stroke="#000000" points="1721.5,-479 1849.5,-479 "/>
+<text text-anchor="start" x="1729.5" y="-467" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="1721.5,-460 1849.5,-460 "/>
+<text text-anchor="start" x="1729.5" y="-448" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1729.5" y="-437" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1729.5" y="-426" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1729.5" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="1729.5" y="-404" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="1729.5" y="-393" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="1729.5" y="-382" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="1729.5" y="-371" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1729.5" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1729.5" y="-349" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1729.5" y="-338" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1729.5" y="-327" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1729.5" y="-316" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="1729.5" y="-305" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1729.5" y="-294" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1729.5" y="-283" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="1729.5" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1729.5" y="-349" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1729.5" y="-338" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node5->Node14 -->
<g id="edge21" class="edge">
<title>Node5->Node14</title>
-<path fill="none" stroke="#191970" d="M1472.4925,-689.3381C1543.6573,-668.8485 1647.8714,-628.8906 1712.5,-559 1739.253,-530.0688 1756.4755,-490.3937 1767.4259,-454.459"/>
-<polygon fill="none" stroke="#191970" points="1471.3551,-686.0222 1462.6777,-692.1012 1473.252,-692.7603 1471.3551,-686.0222"/>
+<path fill="none" stroke="#191970" d="M1472.4925,-744.3381C1543.6573,-723.8485 1647.8714,-683.8906 1712.5,-614 1739.253,-585.0688 1756.4755,-545.3937 1767.4259,-509.459"/>
+<polygon fill="none" stroke="#191970" points="1471.3551,-741.0222 1462.6777,-747.1012 1473.252,-747.7603 1471.3551,-741.0222"/>
</g>
<!-- Node15 -->
<g id="node14" class="node">
<title>Node15</title>
<g id="a_node14"><a xlink:href="classtvm_1_1runtime_1_1Array.html" target="_top" xlink:title="{tvm::runtime::Array\l\< tvm::meta_schedule\l::ScheduleRule \>\n||+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ operator=()\l+ operator=()\land 24 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="1867.5,-270.5 1867.5,-459.5 1995.5,-459.5 1995.5,-270.5 1867.5,-270.5"/>
-<text text-anchor="start" x="1875.5" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Array</text>
-<text text-anchor="start" x="1875.5" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule</text>
-<text text-anchor="middle" x="1931.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::ScheduleRule ></text>
-<polyline fill="none" stroke="#000000" points="1867.5,-418.5 1995.5,-418.5 "/>
-<text text-anchor="middle" x="1931.5" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="1867.5,-399.5 1995.5,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="1867.5,-325.5 1867.5,-514.5 1995.5,-514.5 1995.5,-325.5 1867.5,-325.5"/>
+<text text-anchor="start" x="1875.5" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Array</text>
+<text text-anchor="start" x="1875.5" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule</text>
+<text text-anchor="middle" x="1931.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::ScheduleRule ></text>
+<polyline fill="none" stroke="#000000" points="1867.5,-473.5 1995.5,-473.5 "/>
+<text text-anchor="middle" x="1931.5" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="1867.5,-454.5 1995.5,-454.5 "/>
+<text text-anchor="start" x="1875.5" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1875.5" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1875.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1875.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="1875.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
<text text-anchor="start" x="1875.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
<text text-anchor="start" x="1875.5" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
<text text-anchor="start" x="1875.5" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1875.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1875.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1875.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1875.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1875.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="1875.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1875.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="1875.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 24 more...</text>
+<text text-anchor="start" x="1875.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1875.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="1875.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 24 more...</text>
</a>
</g>
</g>
<!-- Node5->Node15 -->
<g id="edge23" class="edge">
<title>Node5->Node15</title>
-<path fill="none" stroke="#191970" d="M1472.5524,-691.3219C1589.0553,-665.4859 1802.4237,-612.3654 1858.5,-559 1886.1324,-532.7034 1903.3975,-494.9228 1914.143,-459.6769"/>
-<polygon fill="none" stroke="#191970" points="1471.6314,-687.9408 1462.6188,-693.5107 1473.1377,-694.7768 1471.6314,-687.9408"/>
+<path fill="none" stroke="#191970" d="M1472.5524,-746.3219C1589.0553,-720.4859 1802.4237,-667.3654 1858.5,-614 1886.1324,-587.7034 1903.3975,-549.9228 1914.143,-514.6769"/>
+<polygon fill="none" stroke="#191970" points="1471.6314,-742.9408 1462.6188,-748.5107 1473.1377,-749.7768 1471.6314,-742.9408"/>
</g>
<!-- Node16 -->
<g id="node15" class="node">
<title>Node16</title>
<g id="a_node15"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::Target \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="2013.5,-276 2013.5,-454 2141.5,-454 2141.5,-276 2013.5,-276"/>
-<text text-anchor="start" x="2021.5" y="-442" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="middle" x="2077.5" y="-431" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::Target ></text>
-<polyline fill="none" stroke="#000000" points="2013.5,-424 2141.5,-424 "/>
-<text text-anchor="start" x="2021.5" y="-412" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="2013.5,-405 2141.5,-405 "/>
+<polygon fill="#ffffff" stroke="#000000" points="2013.5,-331 2013.5,-509 2141.5,-509 2141.5,-331 2013.5,-331"/>
+<text text-anchor="start" x="2021.5" y="-497" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="middle" x="2077.5" y="-486" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::Target ></text>
+<polyline fill="none" stroke="#000000" points="2013.5,-479 2141.5,-479 "/>
+<text text-anchor="start" x="2021.5" y="-467" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="2013.5,-460 2141.5,-460 "/>
+<text text-anchor="start" x="2021.5" y="-448" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2021.5" y="-437" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2021.5" y="-426" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2021.5" y="-415" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2021.5" y="-404" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="2021.5" y="-393" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="2021.5" y="-382" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="2021.5" y="-371" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2021.5" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2021.5" y="-349" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2021.5" y="-338" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2021.5" y="-327" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2021.5" y="-316" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2021.5" y="-305" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="2021.5" y="-294" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="2021.5" y="-283" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="2021.5" y="-360" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="2021.5" y="-349" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="2021.5" y="-338" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node5->Node16 -->
<g id="edge25" class="edge">
<title>Node5->Node16</title>
-<path fill="none" stroke="#191970" d="M1472.8991,-697.7104C1618.531,-677.8641 1925.7501,-628.7737 2004.5,-559 2034.8016,-532.1523 2052.5686,-491.4361 2062.966,-454.2253"/>
-<polygon fill="none" stroke="#191970" points="1472.1395,-694.2811 1462.6982,-699.0887 1473.0769,-701.2181 1472.1395,-694.2811"/>
+<path fill="none" stroke="#191970" d="M1472.8991,-752.7104C1618.531,-732.8641 1925.7501,-683.7737 2004.5,-614 2034.8016,-587.1523 2052.5686,-546.4361 2062.966,-509.2253"/>
+<polygon fill="none" stroke="#191970" points="1472.1395,-749.2811 1462.6982,-754.0887 1473.0769,-756.2181 1472.1395,-749.2811"/>
</g>
<!-- Node17 -->
<g id="node16" class="node">
<title>Node17</title>
<g id="a_node16"><a xlink:href="classtvm_1_1runtime_1_1Optional.html" target="_top" xlink:title="{tvm::runtime::Optional\l\< tvm::runtime::Array\l\< tvm::meta_schedule::BuilderResult \> \>\n|+ _type_is_nullable\l|+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ Optional()\l+ operator=()\l+ operator=()\land 15 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="2160,-270.5 2160,-459.5 2381,-459.5 2381,-270.5 2160,-270.5"/>
-<text text-anchor="start" x="2168" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
-<text text-anchor="start" x="2168" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Array</text>
-<text text-anchor="middle" x="2270.5" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::BuilderResult > ></text>
-<polyline fill="none" stroke="#000000" points="2160,-418.5 2381,-418.5 "/>
-<text text-anchor="start" x="2168" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="2160,-399.5 2381,-399.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="2160,-325.5 2160,-514.5 2381,-514.5 2381,-325.5 2160,-325.5"/>
+<text text-anchor="start" x="2168" y="-502.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Optional</text>
+<text text-anchor="start" x="2168" y="-491.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Array</text>
+<text text-anchor="middle" x="2270.5" y="-480.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::meta_schedule::BuilderResult > ></text>
+<polyline fill="none" stroke="#000000" points="2160,-473.5 2381,-473.5 "/>
+<text text-anchor="start" x="2168" y="-461.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="2160,-454.5 2381,-454.5 "/>
+<text text-anchor="start" x="2168" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2168" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2168" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2168" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
+<text text-anchor="start" x="2168" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="2168" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="2168" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
<text text-anchor="start" x="2168" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2168" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2168" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2168" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2168" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2168" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Optional()</text>
-<text text-anchor="start" x="2168" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="2168" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="2168" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
+<text text-anchor="start" x="2168" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="2168" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="2168" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 15 more...</text>
</a>
</g>
</g>
<!-- Node5->Node17 -->
<g id="edge27" class="edge">
<title>Node5->Node17</title>
-<path fill="none" stroke="#191970" d="M1472.8355,-700.1528C1642.4549,-682.8048 2040.7772,-634.959 2150.5,-559 2185.8295,-534.542 2212.7674,-495.9677 2232.0806,-459.6363"/>
-<polygon fill="none" stroke="#191970" points="1472.3267,-696.6864 1462.731,-701.1778 1473.0332,-703.6507 1472.3267,-696.6864"/>
+<path fill="none" stroke="#191970" d="M1472.8355,-755.1528C1642.4549,-737.8048 2040.7772,-689.959 2150.5,-614 2185.8295,-589.542 2212.7674,-550.9677 2232.0806,-514.6363"/>
+<polygon fill="none" stroke="#191970" points="1472.3267,-751.6864 1462.731,-756.1778 1473.0332,-758.6507 1472.3267,-751.6864"/>
</g>
<!-- Node6 -->
<g id="node5" class="node">
<title>Node6</title>
<g id="a_node5"><a xlink:href="classtvm_1_1runtime_1_1ObjectPtr.html" target="_top" xlink:title="{tvm::runtime::ObjectPtr\l\< tvm::runtime::Object \>\n||+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ~ObjectPtr()\l+ swap()\l+ get()\l+ operator-\>()\land 11 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="1325.5,-866.5 1325.5,-1044.5 1465.5,-1044.5 1465.5,-866.5 1325.5,-866.5"/>
-<text text-anchor="start" x="1333.5" y="-1032.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
-<text text-anchor="middle" x="1395.5" y="-1021.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
-<polyline fill="none" stroke="#000000" points="1325.5,-1014.5 1465.5,-1014.5 "/>
-<text text-anchor="middle" x="1395.5" y="-1002.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="1325.5,-995.5 1465.5,-995.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="1325.5,-921.5 1325.5,-1099.5 1465.5,-1099.5 1465.5,-921.5 1325.5,-921.5"/>
+<text text-anchor="start" x="1333.5" y="-1087.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
+<text text-anchor="middle" x="1395.5" y="-1076.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
+<polyline fill="none" stroke="#000000" points="1325.5,-1069.5 1465.5,-1069.5 "/>
+<text text-anchor="middle" x="1395.5" y="-1057.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="1325.5,-1050.5 1465.5,-1050.5 "/>
+<text text-anchor="start" x="1333.5" y="-1038.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="1333.5" y="-1027.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="1333.5" y="-1016.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="1333.5" y="-1005.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="1333.5" y="-994.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="1333.5" y="-983.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="1333.5" y="-972.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="1333.5" y="-961.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="1333.5" y="-950.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="1333.5" y="-939.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="1333.5" y="-928.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="1333.5" y="-917.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
-<text text-anchor="start" x="1333.5" y="-906.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
-<text text-anchor="start" x="1333.5" y="-895.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="1333.5" y="-884.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="1333.5" y="-873.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<text text-anchor="start" x="1333.5" y="-972.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
+<text text-anchor="start" x="1333.5" y="-961.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
+<text text-anchor="start" x="1333.5" y="-950.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="1333.5" y="-939.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="1333.5" y="-928.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node6->Node5 -->
<g id="edge5" class="edge">
<title>Node6->Node5</title>
-<path fill="none" stroke="#404040" d="M1395.5,-866.3167C1395.5,-854.8765 1395.5,-843.0062 1395.5,-831.1402"/>
-<polygon fill="none" stroke="#404040" points="1395.5001,-830.7944 1391.5,-824.7944 1395.5,-818.7944 1399.5,-824.7943 1395.5001,-830.7944"/>
-<text text-anchor="middle" x="1415" y="-840" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
+<path fill="none" stroke="#404040" d="M1395.5,-921.3167C1395.5,-909.8765 1395.5,-898.0062 1395.5,-886.1402"/>
+<polygon fill="none" stroke="#404040" points="1395.5001,-885.7944 1391.5,-879.7944 1395.5,-873.7944 1399.5,-879.7943 1395.5001,-885.7944"/>
+<text text-anchor="middle" x="1415" y="-895" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
</g>
<!-- Node7->Node2 -->
<g id="edge6" class="edge">
<title>Node7->Node2</title>
-<path fill="none" stroke="#404040" d="M506.7748,-270.3026C517.7376,-234.0741 536.0284,-195.5918 566.5,-171 662.242,-93.7325 1017.0326,-71.2034 1203.7968,-64.6604"/>
-<polygon fill="none" stroke="#404040" points="1203.858,-64.6584 1209.7191,-60.4575 1215.8511,-64.2521 1209.99,-68.4529 1203.858,-64.6584"/>
-<text text-anchor="middle" x="667" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +space_generator</text>
+<path fill="none" stroke="#404040" d="M507.0795,-325.3321C518.0858,-289.22 536.3267,-250.8148 566.5,-226 662.0751,-147.398 1016.9414,-110.9507 1203.7594,-96.9001"/>
+<polygon fill="none" stroke="#404040" points="1203.85,-96.8935 1209.5381,-92.4611 1215.8172,-96.0068 1210.1292,-100.4392 1203.85,-96.8935"/>
+<text text-anchor="middle" x="654" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +space_generator</text>
</g>
<!-- Node8->Node2 -->
<g id="edge8" class="edge">
<title>Node8->Node2</title>
-<path fill="none" stroke="#404040" d="M723.736,-270.3666C742.8795,-234.1481 769.5498,-195.6559 804.5,-171 867.6654,-126.4394 1071.9916,-93.2412 1203.7835,-75.8025"/>
-<polygon fill="none" stroke="#404040" points="1204.0095,-75.773 1209.4396,-71.0281 1215.908,-74.2155 1210.4779,-78.9604 1204.0095,-75.773"/>
-<text text-anchor="middle" x="904" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +runner_futures</text>
+<path fill="none" stroke="#404040" d="M724.7693,-325.489C743.9785,-289.6216 770.4203,-251.3524 804.5,-226 867.27,-179.3044 1071.7225,-134.8236 1203.6461,-109.951"/>
+<polygon fill="none" stroke="#404040" points="1203.9877,-109.8871 1209.1494,-104.8515 1215.7829,-107.6794 1210.6212,-112.7149 1203.9877,-109.8871"/>
+<text text-anchor="middle" x="894" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +runner_futures</text>
</g>
<!-- Node9->Node2 -->
<g id="edge10" class="edge">
<title>Node9->Node2</title>
-<path fill="none" stroke="#404040" d="M990.7817,-270.3895C1012.6796,-236.559 1040.0645,-199.734 1070.5,-171 1107.8731,-135.7162 1158.5015,-110.7569 1204.4243,-93.7103"/>
-<polygon fill="none" stroke="#404040" points="1204.6973,-93.6121 1208.9867,-87.8155 1215.9873,-89.5455 1211.6978,-95.3421 1204.6973,-93.6121"/>
-<text text-anchor="middle" x="1162" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +measure_candidates</text>
+<path fill="none" stroke="#404040" d="M990.0553,-325.4483C1011.9594,-291.4321 1039.537,-254.4672 1070.5,-226 1109.5114,-190.1331 1159.6702,-160.3753 1204.8075,-137.8969"/>
+<polygon fill="none" stroke="#404040" points="1205.0832,-137.762 1208.7134,-131.5313 1215.861,-132.4858 1212.2308,-138.7166 1205.0832,-137.762"/>
+<text text-anchor="middle" x="1157" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +measure_candidates</text>
</g>
<!-- Node10->Node2 -->
<g id="edge12" class="edge">
<title>Node10->Node2</title>
-<path fill="none" stroke="#404040" d="M1174.6084,-297.7596C1188.8413,-251.675 1211.4677,-190.3713 1242.5,-142 1244.3657,-139.0918 1246.3495,-136.201 1248.4258,-133.3392"/>
-<polygon fill="none" stroke="#404040" points="1248.4922,-133.2528 1248.9768,-126.058 1255.8046,-123.7381 1255.3199,-130.933 1248.4922,-133.2528"/>
-<text text-anchor="middle" x="1279.5" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +logging_func</text>
+<path fill="none" stroke="#404040" d="M1177.3737,-352.6173C1192.6307,-307.2996 1215.3516,-246.946 1242.5,-197 1243.9453,-194.341 1245.4475,-191.6721 1246.9968,-189.0012"/>
+<polygon fill="none" stroke="#404040" points="1247.0028,-188.9911 1246.6666,-181.7879 1253.1865,-178.707 1253.5227,-185.9103 1247.0028,-188.9911"/>
+<text text-anchor="middle" x="1279.5" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +logging_func</text>
</g>
<!-- Node11->Node2 -->
<g id="edge14" class="edge">
<title>Node11->Node2</title>
-<path fill="none" stroke="#404040" d="M1320.5,-275.7288C1320.5,-231.2419 1320.5,-178.0904 1320.5,-135.9211"/>
-<polygon fill="none" stroke="#404040" points="1320.5001,-135.7732 1316.5,-129.7732 1320.5,-123.7732 1324.5,-129.7732 1320.5001,-135.7732"/>
-<text text-anchor="middle" x="1353.5" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +task_name</text>
+<path fill="none" stroke="#404040" d="M1320.5,-330.9973C1320.5,-287.7395 1320.5,-235.5537 1320.5,-190.7779"/>
+<polygon fill="none" stroke="#404040" points="1320.5001,-190.6616 1316.5,-184.6617 1320.5,-178.6616 1324.5,-184.6616 1320.5001,-190.6616"/>
+<text text-anchor="middle" x="1353.5" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +task_name</text>
</g>
<!-- Node12->Node2 -->
<g id="edge16" class="edge">
<title>Node12->Node2</title>
-<path fill="none" stroke="#404040" d="M1445.7199,-270.4048C1432.4028,-229.3676 1413.9657,-181.7191 1390.5,-142 1388.8411,-139.1921 1387.0777,-136.3906 1385.232,-133.608"/>
-<polygon fill="none" stroke="#404040" points="1385.1266,-133.4579 1378.4048,-130.847 1378.2296,-123.638 1384.9514,-126.2489 1385.1266,-133.4579"/>
-<text text-anchor="middle" x="1423" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +postprocs</text>
+<path fill="none" stroke="#404040" d="M1442.4386,-325.2448C1428.6901,-284.8432 1410.8205,-237.7271 1390.5,-197 1389.2206,-194.4358 1387.893,-191.8578 1386.5252,-189.2738"/>
+<polygon fill="none" stroke="#404040" points="1386.4635,-189.1611 1380.0722,-185.8216 1380.6967,-178.6375 1387.0879,-181.977 1386.4635,-189.1611"/>
+<text text-anchor="middle" x="1422" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +postprocs</text>
</g>
<!-- Node13->Node2 -->
<g id="edge18" class="edge">
<title>Node13->Node2</title>
-<path fill="none" stroke="#404040" d="M1602.7329,-270.2087C1589.6974,-235.7701 1570.8867,-198.5811 1544.5,-171 1514.8398,-139.9972 1474.5281,-116.6539 1436.2747,-99.6895"/>
-<polygon fill="none" stroke="#404040" points="1436.0434,-99.5901 1428.9514,-100.8954 1425.0189,-94.851 1432.1109,-93.5457 1436.0434,-99.5901"/>
-<text text-anchor="middle" x="1566" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +mutator_probs</text>
+<path fill="none" stroke="#404040" d="M1600.7505,-325.0078C1587.5803,-291.1347 1569.1944,-254.3802 1544.5,-226 1514.716,-191.7707 1474.1862,-163.5092 1435.7862,-141.7551"/>
+<polygon fill="none" stroke="#404040" points="1435.5196,-141.6074 1428.3328,-142.1988 1425.0227,-135.7923 1432.2095,-135.2009 1435.5196,-141.6074"/>
+<text text-anchor="middle" x="1566" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +mutator_probs</text>
</g>
<!-- Node14->Node2 -->
<g id="edge20" class="edge">
<title>Node14->Node2</title>
-<path fill="none" stroke="#404040" d="M1770.3082,-275.852C1759.7956,-238.8821 1742.1204,-198.3327 1712.5,-171 1672.3427,-133.9442 1537.5539,-101.8673 1437.1793,-82.2851"/>
-<polygon fill="none" stroke="#404040" points="1436.9008,-82.2315 1430.2519,-85.0232 1425.1178,-79.9595 1431.7666,-77.1679 1436.9008,-82.2315"/>
-<text text-anchor="middle" x="1694.5" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +mod</text>
+<path fill="none" stroke="#404040" d="M1769.2909,-330.6344C1758.6152,-294.0696 1741.0934,-253.8924 1712.5,-226 1638.229,-153.5497 1523.5067,-119.4173 1437.3266,-103.4184"/>
+<polygon fill="none" stroke="#404040" points="1437.1754,-103.3915 1430.565,-106.2729 1425.3628,-101.2792 1431.9732,-98.3978 1437.1754,-103.3915"/>
+<text text-anchor="middle" x="1703.5" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +mod</text>
</g>
<!-- Node15->Node2 -->
<g id="edge22" class="edge">
<title>Node15->Node2</title>
-<path fill="none" stroke="#404040" d="M1916.1092,-270.4682C1905.6216,-234.4877 1888.0192,-196.142 1858.5,-171 1796.3049,-118.0274 1576.1051,-87.1189 1437.4377,-72.4807"/>
-<polygon fill="none" stroke="#404040" points="1437.0475,-72.4402 1430.6661,-75.7985 1425.1117,-71.1996 1431.4931,-67.8413 1437.0475,-72.4402"/>
-<text text-anchor="middle" x="1858.5" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +sch_rules</text>
+<path fill="none" stroke="#404040" d="M1915.2666,-325.4299C1904.6628,-289.7716 1887.2011,-251.6689 1858.5,-226 1796.8207,-170.8371 1575.7593,-128.2539 1436.9275,-106.199"/>
+<polygon fill="none" stroke="#404040" points="1436.8582,-106.1882 1430.3094,-109.207 1425.004,-104.3231 1431.5528,-101.3043 1436.8582,-106.1882"/>
+<text text-anchor="middle" x="1858.5" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +sch_rules</text>
</g>
<!-- Node16->Node2 -->
<g id="edge24" class="edge">
<title>Node16->Node2</title>
-<path fill="none" stroke="#404040" d="M2062.8131,-275.9462C2052.3868,-238.7679 2034.6394,-198.0296 2004.5,-171 1922.8687,-97.7913 1610.4105,-73.5714 1437.4336,-65.6955"/>
-<polygon fill="none" stroke="#404040" points="1437.2137,-65.6858 1431.043,-69.4171 1425.2254,-65.1562 1431.3961,-61.4249 1437.2137,-65.6858"/>
-<text text-anchor="middle" x="1989" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +target</text>
+<path fill="none" stroke="#404040" d="M2062.8131,-330.9462C2052.3868,-293.7679 2034.6394,-253.0296 2004.5,-226 1922.2963,-152.278 1610.0813,-114.3197 1437.2916,-98.5838"/>
+<polygon fill="none" stroke="#404040" points="1437.0487,-98.5621 1430.715,-102.0095 1425.0967,-97.489 1431.4304,-94.0415 1437.0487,-98.5621"/>
+<text text-anchor="middle" x="1989" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +target</text>
</g>
<!-- Node17->Node2 -->
<g id="edge26" class="edge">
<title>Node17->Node2</title>
-<path fill="none" stroke="#404040" d="M2231.7706,-270.3653C2212.4395,-234.1466 2185.5717,-195.6546 2150.5,-171 2037.9894,-91.9075 1638.1966,-70.1857 1437.3853,-64.2354"/>
-<polygon fill="none" stroke="#404040" points="1437.3268,-64.2338 1431.2147,-68.0603 1425.3317,-63.8901 1431.4439,-60.0636 1437.3268,-64.2338"/>
-<text text-anchor="middle" x="2159.5" y="-145" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +builder_results</text>
+<path fill="none" stroke="#404040" d="M2231.7706,-325.3653C2212.4395,-289.1466 2185.5717,-250.6546 2150.5,-226 2037.4487,-146.5275 1637.9146,-109.9573 1437.2751,-96.2907"/>
+<polygon fill="none" stroke="#404040" points="1437.2049,-96.2861 1430.9503,-99.8749 1425.2319,-95.4816 1431.4866,-91.8928 1437.2049,-96.2861"/>
+<text text-anchor="middle" x="2159.5" y="-200" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +builder_results</text>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__inherit__graph.svg
index 5e0e97423..7063a81a0 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1TuneContextNode__inherit__graph.svg
@@ -4,88 +4,93 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::meta_schedule::TuneContextNode Pages: 1 -->
-<svg width="217pt" height="699pt"
- viewBox="0.00 0.00 217.00 699.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 695)">
+<svg width="217pt" height="754pt"
+ viewBox="0.00 0.00 217.00 754.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 750)">
<title>tvm::meta_schedule::TuneContextNode</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-695 213,-695 213,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-750 213,-750 213,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-255.5 209,-255.5 209,-.5 0,-.5"/>
-<text text-anchor="start" x="8" y="-243.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
-<text text-anchor="middle" x="104.5" y="-232.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::TuneContextNode</text>
-<polyline fill="none" stroke="#000000" points="0,-225.5 209,-225.5 "/>
-<text text-anchor="start" x="8" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ mod</text>
-<text text-anchor="start" x="8" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ target</text>
-<text text-anchor="start" x="8" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ space_generator</text>
-<text text-anchor="start" x="8" y="-180.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ search_strategy</text>
-<text text-anchor="start" x="8" y="-169.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ sch_rules</text>
-<text text-anchor="start" x="8" y="-158.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ postprocs</text>
-<text text-anchor="start" x="8" y="-147.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ mutator_probs</text>
-<text text-anchor="start" x="8" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ task_name</text>
-<text text-anchor="start" x="8" y="-125.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ logging_func</text>
-<text text-anchor="start" x="8" y="-114.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ rand_state</text>
-<text text-anchor="start" x="8" y="-103.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ num_threads</text>
-<text text-anchor="start" x="8" y="-92.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_terminated</text>
-<text text-anchor="start" x="8" y="-81.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ measure_candidates</text>
-<text text-anchor="start" x="8" y="-70.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ builder_results</text>
-<text text-anchor="start" x="8" y="-59.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ runner_futures</text>
-<text text-anchor="start" x="8" y="-48.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<polyline fill="none" stroke="#000000" points="0,-41.5 209,-41.5 "/>
-<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
-<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Initialize()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-310.5 209,-310.5 209,-.5 0,-.5"/>
+<text text-anchor="start" x="8" y="-298.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
+<text text-anchor="middle" x="104.5" y="-287.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::TuneContextNode</text>
+<polyline fill="none" stroke="#000000" points="0,-280.5 209,-280.5 "/>
+<text text-anchor="start" x="8" y="-268.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ mod</text>
+<text text-anchor="start" x="8" y="-257.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ target</text>
+<text text-anchor="start" x="8" y="-246.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ space_generator</text>
+<text text-anchor="start" x="8" y="-235.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ search_strategy</text>
+<text text-anchor="start" x="8" y="-224.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ sch_rules</text>
+<text text-anchor="start" x="8" y="-213.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ postprocs</text>
+<text text-anchor="start" x="8" y="-202.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ mutator_probs</text>
+<text text-anchor="start" x="8" y="-191.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ task_name</text>
+<text text-anchor="start" x="8" y="-180.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ logging_func</text>
+<text text-anchor="start" x="8" y="-169.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ rand_state</text>
+<text text-anchor="start" x="8" y="-158.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ num_threads</text>
+<text text-anchor="start" x="8" y="-147.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_terminated</text>
+<text text-anchor="start" x="8" y="-136.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ measure_candidates</text>
+<text text-anchor="start" x="8" y="-125.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ builder_results</text>
+<text text-anchor="start" x="8" y="-114.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ runner_futures</text>
+<text text-anchor="start" x="8" y="-103.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<polyline fill="none" stroke="#000000" points="0,-96.5 209,-96.5 "/>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
+<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Initialize()</text>
+<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _SetMeasureCandidates()</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _SendToBuilder()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _SendToRunner()</text>
+<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _Join()</text>
+<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _ClearMeasureState()</text>
<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_FINAL_OBJECT_INFO()</text>
</g>
<!-- Node1 -->
<g id="node2" class="node">
<title>Node1</title>
<g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1Object.html" target="_top" xlink:title="base class of all object containers. ">
-<polygon fill="#ffffff" stroke="#000000" points="13,-292.5 13,-690.5 196,-690.5 196,-292.5 13,-292.5"/>
-<text text-anchor="middle" x="104.5" y="-678.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
-<polyline fill="none" stroke="#000000" points="13,-671.5 196,-671.5 "/>
-<text text-anchor="start" x="21" y="-659.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="21" y="-648.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
-<text text-anchor="start" x="21" y="-637.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
-<text text-anchor="start" x="21" y="-626.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
-<text text-anchor="start" x="21" y="-615.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
-<text text-anchor="start" x="21" y="-604.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
-<text text-anchor="start" x="21" y="-593.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
-<text text-anchor="start" x="21" y="-582.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="21" y="-571.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="21" y="-560.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
-<text text-anchor="start" x="21" y="-549.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="21" y="-538.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="21" y="-527.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
-<text text-anchor="start" x="21" y="-516.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
-<text text-anchor="start" x="21" y="-505.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
-<polyline fill="none" stroke="#000000" points="13,-498.5 196,-498.5 "/>
-<text text-anchor="start" x="21" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
-<text text-anchor="start" x="21" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
-<text text-anchor="start" x="21" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
-<text text-anchor="start" x="21" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
-<text text-anchor="start" x="21" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="21" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="21" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="21" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="21" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
-<text text-anchor="start" x="21" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
-<text text-anchor="start" x="21" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
-<text text-anchor="start" x="21" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
-<text text-anchor="start" x="21" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
-<text text-anchor="start" x="21" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
-<text text-anchor="start" x="21" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
-<text text-anchor="start" x="21" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
+<polygon fill="#ffffff" stroke="#000000" points="13,-347.5 13,-745.5 196,-745.5 196,-347.5 13,-347.5"/>
+<text text-anchor="middle" x="104.5" y="-733.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="13,-726.5 196,-726.5 "/>
+<text text-anchor="start" x="21" y="-714.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="21" y="-703.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="21" y="-692.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="21" y="-681.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="21" y="-670.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="21" y="-659.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="21" y="-648.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="21" y="-637.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="21" y="-626.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="21" y="-615.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="21" y="-604.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="21" y="-593.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="21" y="-582.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="21" y="-571.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<text text-anchor="start" x="21" y="-560.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
+<polyline fill="none" stroke="#000000" points="13,-553.5 196,-553.5 "/>
+<text text-anchor="start" x="21" y="-541.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="21" y="-530.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="21" y="-519.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="21" y="-508.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="21" y="-497.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="21" y="-486.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-475.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="21" y="-453.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="21" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="21" y="-431.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="21" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="21" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="21" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="21" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="21" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="21" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="21" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
</a>
</g>
</g>
<!-- Node1->Node0 -->
<g id="edge1" class="edge">
<title>Node1->Node0</title>
-<path fill="none" stroke="#191970" d="M104.5,-282.3116C104.5,-273.3461 104.5,-264.4718 104.5,-255.7786"/>
-<polygon fill="none" stroke="#191970" points="101.0001,-282.4679 104.5,-292.4679 108.0001,-282.468 101.0001,-282.4679"/>
+<path fill="none" stroke="#191970" d="M104.5,-337.1595C104.5,-328.2091 104.5,-319.2976 104.5,-310.5005"/>
+<polygon fill="none" stroke="#191970" points="101.0001,-337.2773 104.5,-347.2773 108.0001,-337.2773 101.0001,-337.2773"/>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/feature__extractor_8h_source.html b/docs/reference/api/doxygen/feature__extractor_8h_source.html
index 9563844f1..f9d1d138b 100644
--- a/docs/reference/api/doxygen/feature__extractor_8h_source.html
+++ b/docs/reference/api/doxygen/feature__extractor_8h_source.html
@@ -75,7 +75,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyFeatureExtractorNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyFeatureExtractorNode.html">tvm::meta_schedule::PyFeatureExtractorNode</a></div><div class="ttdoc">The feature extractor with customized methods on the python-side. </div><div class="ttdef"><b>Definition:</b> feature_extractor.h:58</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="object_8h_html_aaaa3dc5b6dc33f84b2d28f9a81267212"><div class="ttname"><a href="object_8h.html#aaaa3dc5b6dc33f84b2d28f9a81267212">TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:744</div></div>
-<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuneContext_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuneContext.html">tvm::meta_schedule::TuneContext</a></div><div class="ttdoc">Managed reference to TuneContextNode. </div><div class="ttdef"><b>Definition:</b> tune_context.h:110</div></div>
+<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuneContext_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuneContext.html">tvm::meta_schedule::TuneContext</a></div><div class="ttdoc">Managed reference to TuneContextNode. </div><div class="ttdef"><b>Definition:</b> tune_context.h:129</div></div>
<div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Runtime Array container types. </div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1FeatureExtractorNode_html_ad4e9fdab79326a5bd98745007bb29635"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1FeatureExtractorNode.html#ad4e9fdab79326a5bd98745007bb29635">tvm::meta_schedule::FeatureExtractorNode::ExtractFrom</a></div><div class="ttdeci">virtual Array< tvm::runtime::NDArray > ExtractFrom(const TuneContext &context, const Array< MeasureCandidate > &candidates)=0</div><div class="ttdoc">Extract [...]
diff --git a/docs/reference/api/doxygen/functions__.html b/docs/reference/api/doxygen/functions__.html
index 81d3c4163..29cbdb343 100644
--- a/docs/reference/api/doxygen/functions__.html
+++ b/docs/reference/api/doxygen/functions__.html
@@ -61,9 +61,24 @@ $(function() {
<div class="textblock">Here is a list of all class members with links to the classes they belong to:</div>
<h3><a id="index__"></a>- _ -</h3><ul>
+<li>_ClearMeasureState()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a346cd319a6d696813eff582128efe2cb">tvm::meta_schedule::TuneContextNode</a>
+</li>
<li>_GetOrAllocRuntimeTypeIndex()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a5fbebc47be111ecc1d5869bcc0476e21">tvm::runtime::Object</a>
</li>
+<li>_Join()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a9ba45997fc3c6aa97a351fa1944cb109">tvm::meta_schedule::TuneContextNode</a>
+</li>
+<li>_SendToBuilder()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#aaf53f237cf6958f2e22c3e6dafa68fa0">tvm::meta_schedule::TuneContextNode</a>
+</li>
+<li>_SendToRunner()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4acf21616576112d682bd949ce3e52b9">tvm::meta_schedule::TuneContextNode</a>
+</li>
+<li>_SetMeasureCandidates()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#acd048bfe66a01d00f1af3f69e8ec0881">tvm::meta_schedule::TuneContextNode</a>
+</li>
<li>_type_child_slots
: <a class="el" href="classtvm_1_1arith_1_1IterMapExprNode.html#ab8a4d68ae04e4269485c18f97cd3db21">tvm::arith::IterMapExprNode</a>
, <a class="el" href="classtvm_1_1BaseExprNode.html#a1c4db1562af2034749bc929ed00600a3">tvm::BaseExprNode</a>
diff --git a/docs/reference/api/doxygen/functions_f.html b/docs/reference/api/doxygen/functions_f.html
index c9c7923ef..c569fd9a9 100644
--- a/docs/reference/api/doxygen/functions_f.html
+++ b/docs/reference/api/doxygen/functions_f.html
@@ -359,7 +359,7 @@ $(function() {
: <a class="el" href="classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#aea910ba4ad650db1fbfdd6bc7892ab0c">tvm::meta_schedule::PyTaskSchedulerNode</a>
</li>
<li>FNotifyRunnerResults
-: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">tvm::meta_schedule::PySearchStrategyNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">tvm::meta_schedule::PySearchStrategyNode</a>
</li>
<li>follow_fused_split()
: <a class="el" href="classtvm_1_1auto__scheduler_1_1State.html#a26d72cbcaa97f157076e98ed30a9f477">tvm::auto_scheduler::State</a>
diff --git a/docs/reference/api/doxygen/functions_func.html b/docs/reference/api/doxygen/functions_func.html
index da9ea8f35..aeb9f2608 100644
--- a/docs/reference/api/doxygen/functions_func.html
+++ b/docs/reference/api/doxygen/functions_func.html
@@ -61,9 +61,24 @@ $(function() {
 
<h3><a id="index__"></a>- _ -</h3><ul>
+<li>_ClearMeasureState()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a346cd319a6d696813eff582128efe2cb">tvm::meta_schedule::TuneContextNode</a>
+</li>
<li>_GetOrAllocRuntimeTypeIndex()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a5fbebc47be111ecc1d5869bcc0476e21">tvm::runtime::Object</a>
</li>
+<li>_Join()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a9ba45997fc3c6aa97a351fa1944cb109">tvm::meta_schedule::TuneContextNode</a>
+</li>
+<li>_SendToBuilder()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#aaf53f237cf6958f2e22c3e6dafa68fa0">tvm::meta_schedule::TuneContextNode</a>
+</li>
+<li>_SendToRunner()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#a4acf21616576112d682bd949ce3e52b9">tvm::meta_schedule::TuneContextNode</a>
+</li>
+<li>_SetMeasureCandidates()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1TuneContextNode.html#acd048bfe66a01d00f1af3f69e8ec0881">tvm::meta_schedule::TuneContextNode</a>
+</li>
</ul>
</div><!-- contents -->
<!-- start footer part -->
diff --git a/docs/reference/api/doxygen/functions_func_n.html b/docs/reference/api/doxygen/functions_func_n.html
index 18d295cef..7cfe51a76 100644
--- a/docs/reference/api/doxygen/functions_func_n.html
+++ b/docs/reference/api/doxygen/functions_func_n.html
@@ -122,8 +122,8 @@ $(function() {
: <a class="el" href="classtvm_1_1arith_1_1IntSet.html#a9c2f6e224e86669e9552b4d481ad65ea">tvm::arith::IntSet</a>
</li>
<li>NotifyRunnerResults()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a404a53311309ba8e782a0a0c07e96d19">tvm::meta_schedule::PySearchStrategyNode</a>
-, <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a609a8697917c6041af77478c8f4ef34c">tvm::meta_schedule::SearchStrategyNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a6ae774bd7a6caedf58152c562dae5378">tvm::meta_schedule::PySearchStrategyNode</a>
+, <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a1a5a62e39bbe941f13ec784b43d7e169">tvm::meta_schedule::SearchStrategyNode</a>
</li>
<li>num_inputs()
: <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1MetadataNode.html#a6e76b478a43f97e867727f4cd3036771">tvm::runtime::metadata::MetadataNode</a>
diff --git a/docs/reference/api/doxygen/functions_func_t.html b/docs/reference/api/doxygen/functions_func_t.html
index af4bd3ccc..46327240b 100644
--- a/docs/reference/api/doxygen/functions_func_t.html
+++ b/docs/reference/api/doxygen/functions_func_t.html
@@ -1034,7 +1034,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a41a6b9014d0feeb628ca7edfd0d26f0b">tvm::TypedEnvFunc< R(Args...)></a>
</li>
<li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a6b346a6d0b601eff5a100c7a207e9c86">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a0161d426f9ca366c860ad48c384f7192">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
@@ -1057,7 +1057,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeRelation.html#ac26b1897eab8197ed26606ab81b7403b">tvm::TypeRelation</a>
</li>
<li>TypeReporter()
-: <a class="el" href="classtvm_1_1TypeReporter.html#aa3dc38a3c84d324d0b3a9f358460a091">tvm::TypeReporter</a>
+: <a class="el" href="classtvm_1_1TypeReporter.html#a8e7e05a07f9f7ad9bea91f27afac9051">tvm::TypeReporter</a>
</li>
<li>TypeVar()
: <a class="el" href="classtvm_1_1TypeVar.html#adf5ef8e89d162735519b5d125c89e3e3">tvm::TypeVar</a>
diff --git a/docs/reference/api/doxygen/functions_m.html b/docs/reference/api/doxygen/functions_m.html
index a7c2978ca..cccff13aa 100644
--- a/docs/reference/api/doxygen/functions_m.html
+++ b/docs/reference/api/doxygen/functions_m.html
@@ -306,7 +306,7 @@ $(function() {
: <a class="el" href="classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536">tvm::DiagnosticContextNode</a>
</li>
<li>Module()
-: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9">tvm::runtime::Module</a>
+: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4">tvm::runtime::Module</a>
, <a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d">tvm::runtime::ModuleNode</a>
</li>
<li>module_handle
diff --git a/docs/reference/api/doxygen/functions_n.html b/docs/reference/api/doxygen/functions_n.html
index 9265bde7b..7eea8226b 100644
--- a/docs/reference/api/doxygen/functions_n.html
+++ b/docs/reference/api/doxygen/functions_n.html
@@ -194,8 +194,8 @@ $(function() {
: <a class="el" href="classtvm_1_1arith_1_1IntSet.html#a9c2f6e224e86669e9552b4d481ad65ea">tvm::arith::IntSet</a>
</li>
<li>NotifyRunnerResults()
-: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a404a53311309ba8e782a0a0c07e96d19">tvm::meta_schedule::PySearchStrategyNode</a>
-, <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a609a8697917c6041af77478c8f4ef34c">tvm::meta_schedule::SearchStrategyNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a6ae774bd7a6caedf58152c562dae5378">tvm::meta_schedule::PySearchStrategyNode</a>
+, <a class="el" href="classtvm_1_1meta__schedule_1_1SearchStrategyNode.html#a1a5a62e39bbe941f13ec784b43d7e169">tvm::meta_schedule::SearchStrategyNode</a>
</li>
<li>nparts
: <a class="el" href="classtvm_1_1te_1_1SplitNode.html#a4e809bca962d95b7fab6a98f1617a05c">tvm::te::SplitNode</a>
diff --git a/docs/reference/api/doxygen/functions_s.html b/docs/reference/api/doxygen/functions_s.html
index 1a15bb157..7bbaa60fb 100644
--- a/docs/reference/api/doxygen/functions_s.html
+++ b/docs/reference/api/doxygen/functions_s.html
@@ -808,7 +808,7 @@ $(function() {
</li>
<li>Span()
: <a class="el" href="classtvm_1_1Span.html#a5216631b639e8c802263d87d3fe9e5f6">tvm::Span</a>
-, <a class="el" href="classtvm_1_1support_1_1Span.html#a3c22dd06856e7029e7107adf38eb72f5">tvm::support::Span< T, W ></a>
+, <a class="el" href="classtvm_1_1support_1_1Span.html#a77653730a2542edf93b7c4413a72f3ec">tvm::support::Span< T, W ></a>
</li>
<li>span
: <a class="el" href="classtvm_1_1tir_1_1BufferNode.html#a13fc164e1b65cee741b4895df6316a4a">tvm::tir::BufferNode</a>
@@ -995,7 +995,7 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a93d1d23f24d903db844f75f51fe09a36">tvm::tir::ScheduleNode</a>
</li>
<li>StorageAlignStep()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#af50b7c2f020f8e0a80f5bcc8e559b394">tvm::auto_scheduler::StorageAlignStep</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#a99dbb8c55d9e7d78268b6d43fd348bc7">tvm::auto_scheduler::StorageAlignStep</a>
</li>
<li>StorageType
: <a class="el" href="classtvm_1_1runtime_1_1SimpleObjAllocator_1_1ArrayHandler.html#a67e86db3290b1d3bd4aca7e7a2faf187">tvm::runtime::SimpleObjAllocator::ArrayHandler< ArrayType, ElemType ></a>
@@ -1050,7 +1050,7 @@ $(function() {
, <a class="el" href="classtvm_1_1tir_1_1BufferNode.html#ac18ddd10b79a30ae57d3a8283686259d">tvm::tir::BufferNode</a>
</li>
<li>String()
-: <a class="el" href="classtvm_1_1runtime_1_1String.html#a02fca36e3ff55cc1e83635b02a11fca3">tvm::runtime::String</a>
+: <a class="el" href="classtvm_1_1runtime_1_1String.html#acf549b3c43142639879e0fc31ea5cd77">tvm::runtime::String</a>
, <a class="el" href="classtvm_1_1runtime_1_1StringObj_1_1FromStd.html#a7fb804f7dc96dd9f705c84095f37f1ca">tvm::runtime::StringObj::FromStd</a>
, <a class="el" href="classtvm_1_1runtime_1_1StringObj.html#a7fb804f7dc96dd9f705c84095f37f1ca">tvm::runtime::StringObj</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_t.html b/docs/reference/api/doxygen/functions_t.html
index 8e2b4b14e..ecdae1fb1 100644
--- a/docs/reference/api/doxygen/functions_t.html
+++ b/docs/reference/api/doxygen/functions_t.html
@@ -1178,7 +1178,7 @@ $(function() {
</li>
<li>TVMArgValue
: <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#a7e8b2c6a4fde079ee813c425d2eb6b24">tvm::runtime::ObjectPtr< T ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a987b2fb283cea5484d4655e3f711c046">tvm::runtime::TVMArgValue</a>
+, <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a5fbd71750e5bbba6edc9094178af9276">tvm::runtime::TVMArgValue</a>
</li>
<li>TVMMovableArgValue_
: <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#acd985550cba6cf8509122cbd996c1557">tvm::runtime::ObjectPtr< T ></a>
@@ -1272,7 +1272,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a0d72a6fa7263821c14bcd37837998ed9">tvm::TypedEnvFunc< R(Args...)></a>
</li>
<li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a4abadc6786dd14a3aed6e2b5b342d1d6">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a0161d426f9ca366c860ad48c384f7192">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
diff --git a/docs/reference/api/doxygen/functions_type.html b/docs/reference/api/doxygen/functions_type.html
index 8e62f51c5..0c71528fa 100644
--- a/docs/reference/api/doxygen/functions_type.html
+++ b/docs/reference/api/doxygen/functions_type.html
@@ -185,7 +185,7 @@ $(function() {
: <a class="el" href="classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#aea910ba4ad650db1fbfdd6bc7892ab0c">tvm::meta_schedule::PyTaskSchedulerNode</a>
</li>
<li>FNotifyRunnerResults
-: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#a802c0ead40a90b4bf5c0962a8d4bbdee">tvm::meta_schedule::PySearchStrategyNode</a>
+: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#abfcbc3d1df5bb6d93c0773b069f0eae4">tvm::meta_schedule::PySearchStrategyNode</a>
</li>
<li>FPostTuning
: <a class="el" href="classtvm_1_1meta__schedule_1_1PySearchStrategyNode.html#ad4730dca4fcd0cfbd73fc6c9ed11fe4a">tvm::meta_schedule::PySearchStrategyNode</a>
diff --git a/docs/reference/api/doxygen/hierarchy.html b/docs/reference/api/doxygen/hierarchy.html
index 70caffbb6..4ec7e93c3 100644
--- a/docs/reference/api/doxygen/hierarchy.html
+++ b/docs/reference/api/doxygen/hierarchy.html
@@ -1313,43 +1313,44 @@ This inheritance list is sorted roughly, but not completely, alphabetically:</di
<tr id="row_194_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< String(const Array< ObjectRef > &inputs, const Array< ObjectRef > &attrs, const Optional< ObjectRef > &decision, const Array< String > &outputs)></a></td><td class="desc">< [...]
<tr id="row_195_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< te::Schedule(const Attrs &attrs, const Array< te::Tensor > &outs, const Target &target)></a></td><td class="desc"></td></tr>
<tr id="row_196_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void()></a></td><td class="desc"></td></tr>
-<tr id="row_197_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const Array< tir::Schedule > &, const Optional< Database > &, const Optional< CostModel > &)></a></td><td class="desc"></td></tr>
-<tr id="row_198_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TaskScheduler &task_scheduler, int task_id, const Array< MeasureCandidate > &measure_candidates, const Array< BuilderResult > &builds, const Array< RunnerResult > &result [...]
-<tr id="row_199_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuneContext &)></a></td><td class="desc"></td></tr>
-<tr id="row_200_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuneContext &, const Array< MeasureCandidate > &, const Array< RunnerResult > &)></a></td><td class="desc"></td></tr>
-<tr id="row_201_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuneContext &, const Array< MeasureCandidate > &, void *p_addr)></a></td><td class="desc"></td></tr>
-<tr id="row_202_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuningRecord &)></a></td><td class="desc"></td></tr>
-<tr id="row_203_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(int)></a></td><td class="desc"></td></tr>
-<tr id="row_204_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(size_t, void *)></a></td><td class="desc"></td></tr>
-<tr id="row_205_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(String)></a></td><td class="desc"></td></tr>
-<tr id="row_206_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(tvm::DiagnosticContext ctx)></a></td><td class="desc"></td></tr>
-<tr id="row_207_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< Workload(const IRModule &)></a></td><td class="desc"></td></tr>
-<tr id="row_208_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor.html" target="_self">tvm::TypeFunctor< FType ></a></td><td class="desc"></td></tr>
-<tr id="row_209_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html" target="_self">tvm::TypeFunctor< R(const Type &n, Args...)></a></td><td class="desc"></td></tr>
-<tr id="row_210_" class="even"><td class="entry"><span style="width:0px;display:inline-block;"> </span><span id="arr_210_" class="arrow" onclick="toggleFolder('210_')">►</span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor.html" target="_self">tvm::TypeFunctor< Type(const Type &n)></a></td><td class="desc"></td></tr>
-<tr id="row_210_0_" style="display:none;"><td class="entry"><span style="width:32px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeMutator.html" target="_self">tvm::TypeMutator</a></td><td class="desc"><a class="el" href="classtvm_1_1TypeMutator.html" title="TypeMutator that mutates expressions. ">TypeMutator</a> that mutates expressions </td></tr>
-<tr id="row_211_"><td class="entry"><span style="width:0px;display:inline-block;"> </span><span id="arr_211_" class="arrow" onclick="toggleFolder('211_')">►</span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor.html" target="_self">tvm::TypeFunctor< void(const Type &n)></a></td><td class="desc"></td></tr>
-<tr id="row_211_0_" class="even" style="display:none;"><td class="entry"><span style="width:32px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeVisitor.html" target="_self">tvm::TypeVisitor</a></td><td class="desc">A type visitor that recursively visit types </td></tr>
-<tr id="row_212_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1TypeIndex.html" target="_self">tvm::runtime::TypeIndex</a></td><td class="desc">Namespace for the list of type index </td></tr>
-<tr id="row_213_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName.html" target="_self">tvm::detail::TypeName< T ></a></td><td class="desc">Helper struct to get the type name known to tvm </td></tr>
-<tr id="row_214_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01bool_01_4.html" target="_self">tvm::detail::TypeName< bool ></a></td><td class="desc"></td></tr>
-<tr id="row_215_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01DataType_01_4.html" target="_self">tvm::detail::TypeName< DataType ></a></td><td class="desc"></td></tr>
-<tr id="row_216_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01double_01_4.html" target="_self">tvm::detail::TypeName< double ></a></td><td class="desc"></td></tr>
-<tr id="row_217_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01int_01_4.html" target="_self">tvm::detail::TypeName< int ></a></td><td class="desc"></td></tr>
-<tr id="row_218_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01int64__t_01_4.html" target="_self">tvm::detail::TypeName< int64_t ></a></td><td class="desc"></td></tr>
-<tr id="row_219_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01uint64__t_01_4.html" target="_self">tvm::detail::TypeName< uint64_t ></a></td><td class="desc"></td></tr>
-<tr id="row_220_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01void_01_5_01_4.html" target="_self">tvm::detail::TypeName< void * ></a></td><td class="desc"></td></tr>
-<tr id="row_221_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html" target="_self">tvm::runtime::micro_rpc::Unframer</a></td><td class="desc"></td></tr>
-<tr id="row_222_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1relay_1_1v__info.html" target="_self">tvm::relay::v_info</a></td><td class="desc">A struct to keep info of traversed expr in ExpandDataflow function </td></tr>
-<tr id="row_223_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1Array_1_1ValueConverter.html" target="_self">tvm::runtime::Array< T, typename >::ValueConverter</a></td><td class="desc"></td></tr>
-<tr id="row_224_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1ValueTypeInfoMaker.html" target="_self">tvm::detail::ValueTypeInfoMaker< ValueType, IsArray, IsMap ></a></td><td class="desc"></td></tr>
-<tr id="row_225_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1VirtualDeviceCache.html" target="_self">tvm::VirtualDeviceCache</a></td><td class="desc">A cache of <code>VirtualDevices</code>. This can be used: </td></tr>
-<tr id="row_226_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html" target="_self">tvm::runtime::vm::VMFrame</a></td><td class="desc">A representation of a stack frame </td></tr>
-<tr id="row_227_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html" target="_self">tvm::runtime::vm::VMFunction</a></td><td class="desc">A representation of a Relay function in the VM </td></tr>
-<tr id="row_228_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1With.html" target="_self">tvm::With< ContextType ></a></td><td class="desc">RAII wrapper function to enter and exit a context object similar to python's with syntax </td></tr>
-<tr id="row_229_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1meta__schedule_1_1WorkloadEqual.html" target="_self">tvm::meta_schedule::WorkloadEqual</a></td><td class="desc">The equality check for <a class="el" href="classtvm_1_1meta__schedule_1_1Workload.html" title="Managed reference to WorkloadNode. ">Workload</a> </td></tr>
-<tr id="row_230_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1meta__schedule_1_1WorkloadHash.html" target="_self">tvm::meta_schedule::WorkloadHash</a></td><td class="desc">The hash method for <a class="el" href="classtvm_1_1meta__schedule_1_1Workload.html" title="Managed reference to WorkloadNode. ">Workload</a> </td></tr>
-<tr id="row_231_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1micro__rpc_1_1WriteStream.html" target="_self">tvm::runtime::micro_rpc::WriteStream</a></td><td class="desc"></td></tr>
+<tr id="row_197_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const Array< MeasureCandidate > &, const Array< RunnerResult > &)></a></td><td class="desc"></td></tr>
+<tr id="row_198_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const Array< tir::Schedule > &, const Optional< Database > &, const Optional< CostModel > &)></a></td><td class="desc"></td></tr>
+<tr id="row_199_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TaskScheduler &task_scheduler, int task_id, const Array< MeasureCandidate > &measure_candidates, const Array< BuilderResult > &builds, const Array< RunnerResult > &results)></a></t [...]
+<tr id="row_200_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuneContext &)></a></td><td class="desc"></td></tr>
+<tr id="row_201_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuneContext &, const Array< MeasureCandidate > &, const Array< RunnerResult > &)></a></td><td class="desc"></td></tr>
+<tr id="row_202_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuneContext &, const Array< MeasureCandidate > &, void *p_addr)></a></td><td class="desc"></td></tr>
+<tr id="row_203_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(const TuningRecord &)></a></td><td class="desc"></td></tr>
+<tr id="row_204_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(int)></a></td><td class="desc"></td></tr>
+<tr id="row_205_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(size_t, void *)></a></td><td class="desc"></td></tr>
+<tr id="row_206_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(String)></a></td><td class="desc"></td></tr>
+<tr id="row_207_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< void(tvm::DiagnosticContext ctx)></a></td><td class="desc"></td></tr>
+<tr id="row_208_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_self">tvm::runtime::TypedPackedFunc< Workload(const IRModule &)></a></td><td class="desc"></td></tr>
+<tr id="row_209_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor.html" target="_self">tvm::TypeFunctor< FType ></a></td><td class="desc"></td></tr>
+<tr id="row_210_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor_3_01R_07const_01Type_01_6n_00_01Args_8_8_8_08_4.html" target="_self">tvm::TypeFunctor< R(const Type &n, Args...)></a></td><td class="desc"></td></tr>
+<tr id="row_211_"><td class="entry"><span style="width:0px;display:inline-block;"> </span><span id="arr_211_" class="arrow" onclick="toggleFolder('211_')">►</span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor.html" target="_self">tvm::TypeFunctor< Type(const Type &n)></a></td><td class="desc"></td></tr>
+<tr id="row_211_0_" class="even" style="display:none;"><td class="entry"><span style="width:32px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeMutator.html" target="_self">tvm::TypeMutator</a></td><td class="desc"><a class="el" href="classtvm_1_1TypeMutator.html" title="TypeMutator that mutates expressions. ">TypeMutator</a> that mutates expressions </td></tr>
+<tr id="row_212_" class="even"><td class="entry"><span style="width:0px;display:inline-block;"> </span><span id="arr_212_" class="arrow" onclick="toggleFolder('212_')">►</span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeFunctor.html" target="_self">tvm::TypeFunctor< void(const Type &n)></a></td><td class="desc"></td></tr>
+<tr id="row_212_0_" style="display:none;"><td class="entry"><span style="width:32px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1TypeVisitor.html" target="_self">tvm::TypeVisitor</a></td><td class="desc">A type visitor that recursively visit types </td></tr>
+<tr id="row_213_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1TypeIndex.html" target="_self">tvm::runtime::TypeIndex</a></td><td class="desc">Namespace for the list of type index </td></tr>
+<tr id="row_214_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName.html" target="_self">tvm::detail::TypeName< T ></a></td><td class="desc">Helper struct to get the type name known to tvm </td></tr>
+<tr id="row_215_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01bool_01_4.html" target="_self">tvm::detail::TypeName< bool ></a></td><td class="desc"></td></tr>
+<tr id="row_216_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01DataType_01_4.html" target="_self">tvm::detail::TypeName< DataType ></a></td><td class="desc"></td></tr>
+<tr id="row_217_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01double_01_4.html" target="_self">tvm::detail::TypeName< double ></a></td><td class="desc"></td></tr>
+<tr id="row_218_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01int_01_4.html" target="_self">tvm::detail::TypeName< int ></a></td><td class="desc"></td></tr>
+<tr id="row_219_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01int64__t_01_4.html" target="_self">tvm::detail::TypeName< int64_t ></a></td><td class="desc"></td></tr>
+<tr id="row_220_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01uint64__t_01_4.html" target="_self">tvm::detail::TypeName< uint64_t ></a></td><td class="desc"></td></tr>
+<tr id="row_221_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1TypeName_3_01void_01_5_01_4.html" target="_self">tvm::detail::TypeName< void * ></a></td><td class="desc"></td></tr>
+<tr id="row_222_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html" target="_self">tvm::runtime::micro_rpc::Unframer</a></td><td class="desc"></td></tr>
+<tr id="row_223_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1relay_1_1v__info.html" target="_self">tvm::relay::v_info</a></td><td class="desc">A struct to keep info of traversed expr in ExpandDataflow function </td></tr>
+<tr id="row_224_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1Array_1_1ValueConverter.html" target="_self">tvm::runtime::Array< T, typename >::ValueConverter</a></td><td class="desc"></td></tr>
+<tr id="row_225_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1detail_1_1ValueTypeInfoMaker.html" target="_self">tvm::detail::ValueTypeInfoMaker< ValueType, IsArray, IsMap ></a></td><td class="desc"></td></tr>
+<tr id="row_226_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1VirtualDeviceCache.html" target="_self">tvm::VirtualDeviceCache</a></td><td class="desc">A cache of <code>VirtualDevices</code>. This can be used: </td></tr>
+<tr id="row_227_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html" target="_self">tvm::runtime::vm::VMFrame</a></td><td class="desc">A representation of a stack frame </td></tr>
+<tr id="row_228_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html" target="_self">tvm::runtime::vm::VMFunction</a></td><td class="desc">A representation of a Relay function in the VM </td></tr>
+<tr id="row_229_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1With.html" target="_self">tvm::With< ContextType ></a></td><td class="desc">RAII wrapper function to enter and exit a context object similar to python's with syntax </td></tr>
+<tr id="row_230_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1meta__schedule_1_1WorkloadEqual.html" target="_self">tvm::meta_schedule::WorkloadEqual</a></td><td class="desc">The equality check for <a class="el" href="classtvm_1_1meta__schedule_1_1Workload.html" title="Managed reference to WorkloadNode. ">Workload</a> </td></tr>
+<tr id="row_231_"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="structtvm_1_1meta__schedule_1_1WorkloadHash.html" target="_self">tvm::meta_schedule::WorkloadHash</a></td><td class="desc">The hash method for <a class="el" href="classtvm_1_1meta__schedule_1_1Workload.html" title="Managed reference to WorkloadNode. ">Workload</a> </td></tr>
+<tr id="row_232_" class="even"><td class="entry"><span style="width:16px;display:inline-block;"> </span><span class="icona"><span class="icon">C</span></span><a class="el" href="classtvm_1_1runtime_1_1micro__rpc_1_1WriteStream.html" target="_self">tvm::runtime::micro_rpc::WriteStream</a></td><td class="desc"></td></tr>
</table>
</div><!-- directory -->
</div><!-- contents -->
diff --git a/docs/reference/api/doxygen/inherit_graph_10.svg b/docs/reference/api/doxygen/inherit_graph_10.svg
index bae2058ce..56c3b712b 100644
--- a/docs/reference/api/doxygen/inherit_graph_10.svg
+++ b/docs/reference/api/doxygen/inherit_graph_10.svg
@@ -9,9 +9,9 @@
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 62)">
<title>Graphical Class Hierarchy</title>
<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-62 186,-62 186,4 -4,4"/>
-<!-- Node1218 -->
+<!-- Node1219 -->
<g id="node1" class="node">
-<title>Node1218</title>
+<title>Node1219</title>
<polygon fill="#ffffff" stroke="#bfbfbf" points="0,-19.5 0,-38.5 40,-38.5 40,-19.5 0,-19.5"/>
<text text-anchor="middle" x="20" y="-26.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Error</text>
</g>
@@ -24,24 +24,24 @@
</a>
</g>
</g>
-<!-- Node1218->Node0 -->
+<!-- Node1219->Node0 -->
<g id="edge1" class="edge">
-<title>Node1218->Node0</title>
+<title>Node1219->Node0</title>
<path fill="none" stroke="#191970" d="M50.1726,-34.2594C61.6171,-36.2544 74.8623,-38.5631 87.1902,-40.712"/>
<polygon fill="#191970" stroke="#191970" points="50.6991,-30.7985 40.2466,-32.5292 49.497,-37.6945 50.6991,-30.7985"/>
</g>
-<!-- Node1220 -->
+<!-- Node1221 -->
<g id="node3" class="node">
-<title>Node1220</title>
+<title>Node1221</title>
<g id="a_node3"><a xlink:href="classtvm_1_1CompileError.html" target="_top" xlink:title="Custom Error class to be thrown during compilation. ">
<polygon fill="#ffffff" stroke="#000000" points="76,-.5 76,-19.5 182,-19.5 182,-.5 76,-.5"/>
<text text-anchor="middle" x="129" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::CompileError</text>
</a>
</g>
</g>
-<!-- Node1218->Node1220 -->
+<!-- Node1219->Node1221 -->
<g id="edge2" class="edge">
-<title>Node1218->Node1220</title>
+<title>Node1219->Node1221</title>
<path fill="none" stroke="#191970" d="M50.1333,-23.7474C58.0955,-22.3595 66.9315,-20.8193 75.7249,-19.2865"/>
<polygon fill="#191970" stroke="#191970" points="49.497,-20.3055 40.2466,-25.4708 50.6991,-27.2015 49.497,-20.3055"/>
</g>
diff --git a/docs/reference/api/doxygen/inherit_graph_107.svg b/docs/reference/api/doxygen/inherit_graph_107.svg
index 08c74a04f..de7985214 100644
--- a/docs/reference/api/doxygen/inherit_graph_107.svg
+++ b/docs/reference/api/doxygen/inherit_graph_107.svg
@@ -9,9 +9,9 @@
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 11165)">
<title>Graphical Class Hierarchy</title>
<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-11165 1069,-11165 1069,4 -4,4"/>
-<!-- Node1228 -->
+<!-- Node1229 -->
<g id="node1" class="node">
-<title>Node1228</title>
+<title>Node1229</title>
<g id="a_node1"><a xlink:href="classtvm_1_1runtime_1_1NDArray_1_1ContainerBase.html" target="_top" xlink:title="The container base structure contains all the fields except for the Object header. ">
<polygon fill="#ffffff" stroke="#000000" points="20,-9693 20,-9723 148,-9723 148,-9693 20,-9693"/>
<text text-anchor="start" x="28" y="-9711" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::NDArray</text>
@@ -29,15 +29,15 @@
</a>
</g>
</g>
-<!-- Node1228->Node504 -->
+<!-- Node1229->Node504 -->
<g id="edge1" class="edge">
-<title>Node1228->Node504</title>
+<title>Node1229->Node504</title>
<path fill="none" stroke="#191970" d="M158.2796,-9707.3278C184.9735,-9707.0862 214.8383,-9706.8159 240.6206,-9706.5826"/>
<polygon fill="#191970" stroke="#191970" points="158.1871,-9703.8284 148.2192,-9707.4188 158.2505,-9710.8281 158.1871,-9703.8284"/>
</g>
-<!-- Node1175 -->
+<!-- Node1176 -->
<g id="node3" class="node">
-<title>Node1175</title>
+<title>Node1176</title>
<g id="a_node3"><a xlink:href="classtvm_1_1runtime_1_1InplaceArrayBase.html" target="_top" xlink:title="Base template for classes with array like memory layout. ">
<polygon fill="#ffffff" stroke="#000000" points="222.5,-2542 222.5,-2572 387.5,-2572 387.5,-2542 222.5,-2542"/>
<text text-anchor="start" x="230.5" y="-2560" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::InplaceArray</text>
@@ -54,15 +54,15 @@
</a>
</g>
</g>
-<!-- Node1175->Node496 -->
+<!-- Node1176->Node496 -->
<g id="edge2" class="edge">
-<title>Node1175->Node496</title>
+<title>Node1176->Node496</title>
<path fill="none" stroke="#191970" d="M396.3329,-2541.0543C399.8769,-2538.4319 403.1333,-2535.4308 406,-2532 486.2427,-2435.967 359.373,-2063.9894 442,-1970 446.8961,-1964.4306 452.8983,-1960.1961 459.4968,-1957.0052"/>
<polygon fill="#191970" stroke="#191970" points="394.2206,-2538.2468 387.5897,-2546.51 397.9264,-2544.1855 394.2206,-2538.2468"/>
</g>
-<!-- Node1174 -->
+<!-- Node1175 -->
<g id="node5" class="node">
-<title>Node1174</title>
+<title>Node1175</title>
<g id="a_node5"><a xlink:href="classtvm_1_1runtime_1_1InplaceArrayBase.html" target="_top" xlink:title="tvm::runtime::InplaceArray\lBase\< ADTObj, ObjectRef \>">
<polygon fill="#ffffff" stroke="#000000" points="7.5,-9644 7.5,-9674 160.5,-9674 160.5,-9644 7.5,-9644"/>
<text text-anchor="start" x="15.5" y="-9662" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::InplaceArray</text>
@@ -79,15 +79,15 @@
</a>
</g>
</g>
-<!-- Node1174->Node489 -->
+<!-- Node1175->Node489 -->
<g id="edge3" class="edge">
-<title>Node1174->Node489</title>
+<title>Node1175->Node489</title>
<path fill="none" stroke="#191970" d="M170.9456,-9659C195.1707,-9659 220.9797,-9659 243.4174,-9659"/>
<polygon fill="#191970" stroke="#191970" points="170.6749,-9655.5001 160.6748,-9659 170.6748,-9662.5001 170.6749,-9655.5001"/>
</g>
-<!-- Node1173 -->
+<!-- Node1174 -->
<g id="node7" class="node">
-<title>Node1173</title>
+<title>Node1174</title>
<g id="a_node7"><a xlink:href="classtvm_1_1runtime_1_1InplaceArrayBase.html" target="_top" xlink:title="tvm::runtime::InplaceArray\lBase\< ArrayNode, ObjectRef \>">
<polygon fill="#ffffff" stroke="#000000" points="0,-9595 0,-9625 168,-9625 168,-9595 0,-9595"/>
<text text-anchor="start" x="8" y="-9613" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::InplaceArray</text>
@@ -104,9 +104,9 @@
</a>
</g>
</g>
-<!-- Node1173->Node490 -->
+<!-- Node1174->Node490 -->
<g id="edge4" class="edge">
-<title>Node1173->Node490</title>
+<title>Node1174->Node490</title>
<path fill="none" stroke="#191970" d="M178.2093,-9614.6892C197.5291,-9615.6508 217.5282,-9616.6462 235.774,-9617.5544"/>
<polygon fill="#191970" stroke="#191970" points="178.3427,-9611.1916 168.1811,-9614.19 177.9947,-9618.1829 178.3427,-9611.1916"/>
</g>
diff --git a/docs/reference/api/doxygen/inherit_graph_162.svg b/docs/reference/api/doxygen/inherit_graph_162.svg
index ce96f228c..34a550999 100644
--- a/docs/reference/api/doxygen/inherit_graph_162.svg
+++ b/docs/reference/api/doxygen/inherit_graph_162.svg
@@ -4,21 +4,20 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: Graphical Class Hierarchy Pages: 1 -->
-<svg width="181pt" height="72pt"
- viewBox="0.00 0.00 181.00 72.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 68)">
+<svg width="192pt" height="61pt"
+ viewBox="0.00 0.00 192.00 61.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 57)">
<title>Graphical Class Hierarchy</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-68 177,-68 177,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-57 188,-57 188,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<g id="a_node1"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="tvm::runtime::TypedPacked\lFunc\< void(const Array\l\< tir::Schedule \> &, const\l Optional\< Database \> &, const\l Optional\< CostModel \> &)\>">
-<polygon fill="#ffffff" stroke="#000000" points="0,-.5 0,-63.5 173,-63.5 173,-.5 0,-.5"/>
-<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
-<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const Array</text>
-<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tir::Schedule > &, const</text>
-<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> Optional< Database > &, const</text>
-<text text-anchor="middle" x="86.5" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> Optional< CostModel > &)></text>
+<g id="a_node1"><a xlink:href="classtvm_1_1runtime_1_1TypedPackedFunc.html" target="_top" xlink:title="tvm::runtime::TypedPacked\lFunc\< void(const Array\l\< MeasureCandidate \> &,\l const Array\< RunnerResult \> &)\>">
+<polygon fill="#ffffff" stroke="#000000" points="0,-.5 0,-52.5 184,-52.5 184,-.5 0,-.5"/>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::TypedPacked</text>
+<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Func< void(const Array</text>
+<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< MeasureCandidate > &,</text>
+<text text-anchor="middle" x="92" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> const Array< RunnerResult > &)></text>
</a>
</g>
</g>
diff --git a/docs/reference/api/doxygen/inherit_graph_163.svg b/docs/reference/api/doxygen/inherit_graph_163.svg
... 5927 lines suppressed ...