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 2022/05/28 01:45:48 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@afb67e64a1891e1d1aab03c4614fca11473e7b27)
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 a92b7b3e8 deploying docs (apache/tvm@afb67e64a1891e1d1aab03c4614fca11473e7b27)
a92b7b3e8 is described below
commit a92b7b3e82368080ac0307f0a7c45839cdc1b6c4
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat May 28 01:45:43 2022 +0000
deploying docs (apache/tvm@afb67e64a1891e1d1aab03c4614fca11473e7b27)
---
.../how_to/compile_models/from_coreml.rst.txt | 2 +-
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 4 +-
.../how_to/compile_models/from_oneflow.rst.txt | 4 +-
.../how_to/compile_models/from_onnx.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 4 +-
.../how_to/compile_models/from_pytorch.rst.txt | 4 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 4 +-
.../how_to/compile_models/from_tflite.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 4 +-
.../deploy_models/deploy_model_on_rasp.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 6 +-
.../deploy_models/deploy_prequantized.rst.txt | 8 +-
.../deploy_prequantized_tflite.rst.txt | 6 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 4 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 6 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 6 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_infra.rst.txt | 2 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 18 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 6 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 6 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 18 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 1359 +-------------------
.../tune_network_arm.rst.txt | 2 +-
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_mali.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 6 +-
.../tune_sparse_x86.rst.txt | 91 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 102 +-
.../tune_with_autotvm/tune_relay_cuda.rst.txt | 2 +-
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/using_external_lib.rst.txt | 4 +-
.../how_to/work_with_schedules/extern_op.rst.txt | 9 -
.../how_to/work_with_schedules/intrin_math.rst.txt | 10 -
.../how_to/work_with_schedules/reduction.rst.txt | 4 -
.../how_to/work_with_schedules/scan.rst.txt | 11 -
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 11 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../vta/tutorials/autotvm/tune_relay_vta.rst.txt | 2 +-
.../frontend/deploy_classification.rst.txt | 4 +-
.../tutorials/frontend/deploy_detection.rst.txt | 4 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/matrix_multiply.rst.txt | 2 +-
.../vta/tutorials/optimize/convolution_opt.rst.txt | 2 +-
.../tutorials/optimize/matrix_multiply_opt.rst.txt | 2 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/vta_get_started.rst.txt | 2 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 14 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 9 -
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 11 +-
docs/_sources/tutorial/intro_topi.rst.txt | 15 +-
docs/_sources/tutorial/relay_quick_start.rst.txt | 4 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 48 +-
.../tutorial/tensor_ir_blitz_course.rst.txt | 4 -
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_coreml.html | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 4 +-
docs/how_to/compile_models/from_oneflow.html | 73 +-
docs/how_to/compile_models/from_onnx.html | 2 +-
docs/how_to/compile_models/from_paddle.html | 4 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 4 +-
docs/how_to/compile_models/from_tflite.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 4 +-
.../how_to/deploy_models/deploy_model_on_rasp.html | 2 +-
.../deploy_object_detection_pytorch.html | 43 +-
docs/how_to/deploy_models/deploy_prequantized.html | 12 +-
.../deploy_models/deploy_prequantized_tflite.html | 6 +-
docs/how_to/deploy_models/deploy_quantized.html | 4 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 6 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_infra.html | 2 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 18 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 6 +-
.../optimize_operators/opt_conv_tensorcore.html | 6 +-
docs/how_to/optimize_operators/opt_gemm.html | 18 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1358 +------------------
.../tune_with_autoscheduler/tune_network_arm.html | 2 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_mali.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 6 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 90 +-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 102 +-
docs/how_to/tune_with_autotvm/tune_relay_cuda.html | 2 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/using_external_lib.html | 4 +-
docs/how_to/work_with_schedules/extern_op.html | 5 -
docs/how_to/work_with_schedules/intrin_math.html | 22 +-
docs/how_to/work_with_schedules/reduction.html | 7 +-
docs/how_to/work_with_schedules/scan.html | 7 -
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 7 +-
docs/reference/api/python/auto_scheduler.html | 6 +-
.../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 +-
.../vta/tutorials/autotvm/tune_relay_vta.html | 2 +-
.../tutorials/frontend/deploy_classification.html | 4 +-
.../vta/tutorials/frontend/deploy_detection.html | 4 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/matrix_multiply.html | 2 +-
.../vta/tutorials/optimize/convolution_opt.html | 2 +-
.../tutorials/optimize/matrix_multiply_opt.html | 2 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/vta_get_started.html | 2 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 5 -
docs/tutorial/autotvm_relay_x86.html | 199 +--
docs/tutorial/cross_compilation_and_rpc.html | 7 +-
docs/tutorial/intro_topi.html | 11 +-
docs/tutorial/relay_quick_start.html | 4 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 48 +-
docs/tutorial/tensor_ir_blitz_course.html | 8 +-
159 files changed, 1203 insertions(+), 3752 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_coreml.rst.txt b/docs/_sources/how_to/compile_models/from_coreml.rst.txt
index 9a004b090..922337379 100644
--- a/docs/_sources/how_to/compile_models/from_coreml.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_coreml.rst.txt
@@ -107,7 +107,7 @@ We should be familiar with the process right now.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 2bdb67d0e..4ff96d5e1 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -144,7 +144,7 @@ compile the model
.. code-block:: none
Compiling the model...
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 c10a764f4..c244783c0 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.zipd8f044fe-824c-41a8-8070-245e5b9649de from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf9610e5c-542d-4ecc-9997-c78b02f2b607 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
@@ -143,7 +143,7 @@ now compile the graph
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 f2d5bd153..209927aa3 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<07:22, 98.2kB/s]
0%| | 48.0k/41.5M [00:00<04:39, 155kB/s]
0%| | 96.0k/41.5M [00:00<03:18, 218kB/s]
0%| | 192k/41.5M [00:00<01:59, 364kB/s]
1%| | 392k/41.5M [00:00<01:04, 673kB/s]
2%|1 | 656k/41.5M [00:01<00:43, 992kB/s]
3%|3 | 1.29M/41.5M [00:01<00:21, 1.99MB/s]
6%|5 | 2.47M/41.5M [00:01<00:11, 3.71MB/s]
10%|9 | 3.96M/41.5M [00:01<00:07, 5.46MB/s]
13%|#3 | 5.45M/41.5M [00:01<00:05, 6.64MB/s]
17%|#6 | 6.93M/41.5M [00:01<00:04, 7.45MB/s]
20%|## | 8.41M/41.5M [00:02<00:04, 8.00MB/s]
24%|##3 | 9.90M/41.5M [00:02<00:03, 8.39MB/s]
27%|##7 | 11.4M/41.5M [00:02<00:03, 8.65MB/s]
31%|### | 12.9M/41.5M [00:02<00:03, 8.83MB/s]
35%|###4 | 14.3M/41.5M [00:02<00:03, 8.96MB/s]
38%|###8 | 15.8M/41.5M [00:02<00
:02, 9.05MB/s]
42%|####1 | 17.3M/41.5M [00:03<00:02, 9.12MB/s]
45%|####5 | 18.8M/41.5M [00:03<00:02, 9.15MB/s]
49%|####8 | 20.3M/41.5M [00:03<00:02, 9.19MB/s]
52%|#####2 | 21.8M/41.5M [00:03<00:02, 9.22MB/s]
56%|#####6 | 23.2M/41.5M [00:03<00:02, 9.23MB/s]
60%|#####9 | 24.7M/41.5M [00:03<00:01, 9.25MB/s]
63%|######3 | 26.2M/41.5M [00:04<00:01, 9.26MB/s]
67%|######6 | 27.7M/41.5M [00:04<00:01, 9.26MB/s]
70%|####### | 29.2M/41.5M [00:04<00:01, 9.27MB/s]
74%|#######3 | 30.7M/41.5M [00:04<00:01, 9.27MB/s]
78%|#######7 | 32.2M/41.5M [00:04<00:01, 9.29MB/s]
81%|########1 | 33.6M/41.5M [00:04<00:00, 9.27MB/s]
85%|########4 | 35.1M/41.5M [00:05<00:00, 9.27MB/s]
88%|########8 | 36.6M/41.5M [00:05<00:00, 9.27MB/s]
92%|#########1| 38.1M/41.5M [00:05<00:00, 9.27MB/s]
95%|#########5| 39.6M/41.5M [00:05<00:00, 9.27MB/s]
99%|#########8| 41.1M/41.5M [00:05<00:00, 9.27MB/s]
100%|####
######| 41.5M/41.5M [00:05<00:00, 7.62MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:54, 91.7kB/s]
0%| | 48.0k/41.5M [00:00<04:59, 145kB/s]
0%| | 96.0k/41.5M [00:00<03:32, 204kB/s]
0%| | 168k/41.5M [00:00<02:31, 285kB/s]
1%| | 336k/41.5M [00:00<01:21, 528kB/s]
2%|1 | 680k/41.5M [00:01<00:42, 1.01MB/s]
3%|3 | 1.34M/41.5M [00:01<00:21, 1.96MB/s]
6%|6 | 2.68M/41.5M [00:01<00:10, 3.83MB/s]
10%|9 | 4.15M/41.5M [00:01<00:07, 5.31MB/s]
14%|#3 | 5.61M/41.5M [00:01<00:05, 6.30MB/s]
17%|#7 | 7.09M/41.5M [00:01<00:05, 7.01MB/s]
21%|## | 8.55M/41.5M [00:02<00:04, 7.48MB/s]
24%|##4 | 10.0M/41.5M [00:02<00:03, 8.99MB/s]
28%|##7 | 11.5M/41.5M [00:02<00:03, 9.56MB/s]
30%|### | 12.5M/41.5M [00:02<00:03, 9.18MB/s]
32%|###2 | 13.4M/41.5M [00:02<00:03, 7.89MB/s]
35%|###4 | 14.4M/41.5M [00:02<0
0:03, 7.36MB/s]
38%|###8 | 15.9M/41.5M [00:03<00:03, 7.75MB/s]
42%|####1 | 17.4M/41.5M [00:03<00:03, 8.01MB/s]
45%|####5 | 18.8M/41.5M [00:03<00:02, 8.19MB/s]
49%|####8 | 20.3M/41.5M [00:03<00:02, 8.30MB/s]
52%|#####2 | 21.8M/41.5M [00:03<00:02, 8.38MB/s]
56%|#####6 | 23.2M/41.5M [00:03<00:02, 8.43MB/s]
60%|#####9 | 24.7M/41.5M [00:04<00:02, 8.47MB/s]
63%|######3 | 26.2M/41.5M [00:04<00:01, 8.50MB/s]
67%|######6 | 27.6M/41.5M [00:04<00:01, 8.52MB/s]
70%|####### | 29.1M/41.5M [00:04<00:01, 8.54MB/s]
74%|#######3 | 30.6M/41.5M [00:04<00:01, 8.55MB/s]
77%|#######7 | 32.1M/41.5M [00:05<00:01, 8.55MB/s]
81%|######## | 33.5M/41.5M [00:05<00:00, 8.56MB/s]
84%|########4 | 35.0M/41.5M [00:05<00:00, 8.56MB/s]
88%|########7 | 36.5M/41.5M [00:05<00:00, 8.56MB/s]
91%|#########1| 37.9M/41.5M [00:05<00:00, 8.56MB/s]
95%|#########4| 39.4M/41.5M [00:05<00:00, 8.55MB/s]
98%|###
######8| 40.9M/41.5M [00:06<00:00, 9.79MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 7.11MB/s]
@@ -187,7 +187,7 @@ Compile the graph to llvm target with given input specification.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/how_to/compile_models/from_onnx.rst.txt b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
index 10992f76d..49a641ad4 100644
--- a/docs/_sources/how_to/compile_models/from_onnx.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
@@ -132,7 +132,7 @@ provides a static definition of the input size.
==> Context: Bad node spec for node. Name: OpType: Conv
warnings.warn(str(e))
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 dd6677496..d6b802747 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -149,7 +149,7 @@ Compile the model with relay
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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 8.803 seconds)
+ **Total running time of the script:** ( 1 minutes 9.684 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 9edced1a9..96be83199 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]
43%|####3 | 19.3M/44.7M [00:00<00:00, 202MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 236MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
39%|###8 | 17.3M/44.7M [00:00<00:00, 182MB/s]
98%|#########7| 43.8M/44.7M [00:00<00:00, 238MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 230MB/s]
@@ -155,7 +155,7 @@ Compile the graph to llvm target with given input specification.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 4ac14c8bc..fab234544 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -231,7 +231,7 @@ Results:
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -381,7 +381,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.015 seconds)
+ **Total running time of the script:** ( 1 minutes 3.097 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/from_tflite.rst.txt b/docs/_sources/how_to/compile_models/from_tflite.rst.txt
index 443ccadf9..24e4a9fb1 100644
--- a/docs/_sources/how_to/compile_models/from_tflite.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tflite.rst.txt
@@ -186,7 +186,7 @@ Compile the model with relay
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 86e6fd2e6..2d13b6468 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
=================
-**05:28.091** total execution time for **how_to_compile_models** files:
+**05:20.996** total execution time for **how_to_compile_models** files:
-- **01:08.803**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:03.015**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:58.727**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:31.632**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:24.481**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:22.662**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:22.627**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:19.584**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.027**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.533**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:09.684**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:03.097**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:58.035**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:29.793**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:25.065**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.155**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:20.670**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:18.986**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:11.921**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.590**: :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 8a05a5c84..90372b1c9 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
@@ -320,7 +320,7 @@ to run this tutorial with a real device.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -402,7 +402,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 17.0659 17.2262 17.4522 16.3691 0.3964
+ 15.4771 15.4744 15.5467 15.4272 0.0315
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt
index 2323db442..1386dead2 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt
@@ -254,7 +254,7 @@ to run this tutorial with a real device.
/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,
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 66d93acb1..c030530d2 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]
7%|6 | 11.5M/170M [00:00<00:01, 120MB/s]
14%|#3 | 23.0M/170M [00:00<00:01, 119MB/s]
26%|##5 | 43.4M/170M [00:00<00:00, 162MB/s]
39%|###9 | 66.5M/170M [00:00<00:00, 194MB/s]
50%|##### | 85.0M/170M [00:00<00:00, 189MB/s]
64%|######4 | 109M/170M [00:00<00:00, 209MB/s]
76%|#######5 | 129M/170M [00:00<00:00, 203MB/s]
88%|########8 | 150M/170M [00:00<00:00, 208MB/s]
100%|##########| 170M/170M [00:00<00:00, 197MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.95M/170M [00:00<00:04, 41.2MB/s]
5%|4 | 8.38M/170M [00:00<00:03, 44.3MB/s]
8%|7 | 13.3M/170M [00:00<00:03, 47.5MB/s]
10%|# | 17.8M/170M [00:00<00:03, 43.3MB/s]
13%|#2 | 22.0M/170M [00:00<00:03, 40.0MB/s]
16%|#5 | 26.9M/170M [00:00<00:03, 43.4MB/s]
19%|#8 | 31.5M/170M [00:00<00:03, 45.0MB/s]
21%|##1 | 35.9M/170M [00:00<00:03, 44.8MB/s]
24%|##3 | 40.2M/170M [00:00<00:03, 40.9MB/s]
26%|##6 | 44.3M/170M [00:01<00:03, 41.5MB/s]
30%|##9 | 50.1M/170M [00:01<00:02, 46.6MB/s]
32%|###2 | 54.6M/170M [00:01<00:02, 45.1MB/s]
35%|###5 | 60.0M/170M [00:01<00:02, 48.1MB/s]
38%|###8 | 64.6M/170M [00:01<00:02, 46.6MB/s]
41%|####1 | 70.3M/170M [00:01<00:02, 50.2MB/s]
44%|####4 | 75.1M/170M [00:01<00:02, 44.1MB/s]
47%|####6 | 79.5M/170M [00:01<00:02, 36.9MB/
s]
49%|####9 | 83.6M/170M [00:02<00:02, 38.5MB/s]
52%|#####1 | 87.5M/170M [00:02<00:02, 38.8MB/s]
54%|#####3 | 91.4M/170M [00:02<00:02, 39.2MB/s]
56%|#####6 | 95.3M/170M [00:02<00:02, 37.2MB/s]
58%|#####8 | 98.9M/170M [00:02<00:02, 35.8MB/s]
60%|###### | 102M/170M [00:02<00:02, 30.7MB/s]
63%|######3 | 107M/170M [00:02<00:01, 35.0MB/s]
66%|######5 | 112M/170M [00:02<00:01, 38.5MB/s]
68%|######8 | 116M/170M [00:02<00:01, 41.4MB/s]
72%|#######1 | 122M/170M [00:03<00:01, 46.0MB/s]
85%|########5 | 145M/170M [00:03<00:00, 101MB/s]
99%|#########8| 168M/170M [00:03<00:00, 142MB/s]
100%|##########| 170M/170M [00:03<00:00, 54.6MB/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').
@@ -207,7 +207,7 @@ torchvision rcnn models.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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 16.965 seconds)
+ **Total running time of the script:** ( 3 minutes 2.402 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 187a842d7..c63f0de93 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]
22%|##2 | 3.05M/13.6M [00:00<00:00, 31.3MB/s]
48%|####7 | 6.48M/13.6M [00:00<00:00, 33.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 60.5MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
16%|#5 | 2.14M/13.6M [00:00<00:00, 22.3MB/s]
37%|###7 | 5.02M/13.6M [00:00<00:00, 26.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 51.9MB/s]
@@ -274,7 +274,7 @@ standard Relay operators before compilation.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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)
- 90.6628 90.5379 94.8582 90.3709 0.6191
+ 90.4832 90.5345 90.7676 89.8992 0.2472
@@ -393,7 +393,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.707 seconds)
+ **Total running time of the script:** ( 1 minutes 3.824 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 040da2d75..428e69a8a 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
@@ -289,7 +289,7 @@ target platform that you are interested in.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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)
- 122.6569 122.6277 123.4709 121.9520 0.3226
+ 119.5748 119.3936 120.9184 117.3421 0.6355
@@ -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 54.061 seconds)
+ **Total running time of the script:** ( 1 minutes 51.731 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 3ecb859d3..5e37ec421 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -213,7 +213,7 @@ We create a Relay VM to build and execute the model.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/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,
@@ -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 27.394 seconds)
+ **Total running time of the script:** ( 1 minutes 8.716 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 d6594ad87..2ebe83297 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%|5 | 7056/132723 [00:00<00:01, 70554.18KB/s]
12%|#1 | 15397/132723 [00:00<00:01, 78107.78KB/s]
18%|#7 | 23875/132723 [00:00<00:01, 81147.81KB/s]
24%|##4 | 32347/132723 [00:00<00:01, 82553.31KB/s]
31%|### | 40814/132723 [00:00<00:01, 83315.20KB/s]
37%|###7 | 49300/132723 [00:00<00:00, 83838.79KB/s]
44%|####3 | 57779/132723 [00:00<00:00, 84146.03KB/s]
50%|####9 | 66194/132723 [00:00<00:00, 83874.42KB/s]
56%|#####6 | 74713/132723 [00:00<00:00, 84279.33KB/s]
63%|######2 | 83247/132723 [00:01<00:00, 84603.85KB/s]
69%|######9 | 91772/132723 [00:01<00:00, 84796.95KB/s]
76%|#######5 | 100359/132723 [00:01<00:00, 85120.98KB/s]
82%|########2 | 109031/132723 [00:01<00:00, 85602.95KB/s]
89%|########8 | 117592/132723 [00:01<00:00, 85559.16KB/s]
95%|#########5| 126318/132723 [00:01<00:00, 86069.30KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84143.39KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6624/132723 [00:00<00:01, 66233.75KB/s]
12%|#1 | 15411/132723 [00:00<00:01, 78954.64KB/s]
18%|#8 | 24166/132723 [00:00<00:01, 82875.38KB/s]
25%|##4 | 32946/132723 [00:00<00:01, 84812.20KB/s]
31%|###1 | 41720/132723 [00:00<00:01, 85867.03KB/s]
38%|###8 | 50513/132723 [00:00<00:00, 86567.51KB/s]
45%|####4 | 59245/132723 [00:00<00:00, 86810.42KB/s]
51%|#####1 | 68091/132723 [00:00<00:00, 87333.44KB/s]
58%|#####7 | 76933/132723 [00:00<00:00, 87669.40KB/s]
65%|######4 | 85700/132723 [00:01<00:00, 87505.83KB/s]
71%|#######1 | 94451/132723 [00:01<00:00, 87335.74KB/s]
78%|#######7 | 103234/132723 [00:01<00:00, 87484.39KB/s]
84%|########4 | 111983/132723 [00:01<00:00, 87308.32KB/s]
91%|######### | 120734/132723 [00:01<00:00, 87367.85KB/s]
98%|#########7| 129511/132723 [00:01<00:00, 87486.12KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 86136.72KB/s]
@@ -180,7 +180,7 @@ Create TVM runtime and do inference
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -211,7 +211,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 32.795 seconds)
+ **Total running time of the script:** ( 2 minutes 19.691 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 367516efc..143574bcb 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
=================
-**11:14.091** total execution time for **how_to_deploy_models** files:
+**10:14.970** total execution time for **how_to_deploy_models** files:
-- **03:16.965**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:32.795**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:54.061**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:27.394**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:09.707**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:30.382**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.577**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.211**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:02.402**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:19.691**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:51.731**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:08.716**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:03.824**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.462**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:20.964**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.180**: :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 eed4fc16e..b71980fce 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
@@ -116,7 +116,7 @@ Finally, we're ready to run the program:
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
z: [0.7996937 1.168008 1.4516819]
@@ -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.zip15295a23-de49-4ba7-b230-e81e8057d888 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip23265740-86f7-4464-8b57-beefc963940c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -527,7 +527,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
.. code-block:: none
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
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 16b4fcbcf..ce944363d 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
=================
-**00:39.910** total execution time for **how_to_extend_tvm** files:
+**00:37.455** total execution time for **how_to_extend_tvm** files:
-- **00:36.186**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.377**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.130**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.218**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.075**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.182**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.008**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.190**: :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_infra.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_infra.rst.txt
index b0f5c900c..ce5d7099f 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_infra.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_infra.rst.txt
@@ -119,7 +119,7 @@ Manually Apply Optimization Passes
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%0 = nn.conv2d(%x, %weight, padding=[0, 0, 0, 0]) /* ty=Tensor[(1, 64, 54, 54), float32] */;
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 e6082b5ff..3b786a601 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: 6494us [6494us] (45.82%; 45.82%)
- FoldScaleAxis: 7677us [3us] (54.18%; 54.18%)
- FoldConstant: 7674us [1580us] (54.15%; 99.96%)
- InferType: 6094us [6094us] (43.00%; 79.41%)
+ InferType: 5969us [5969us] (45.49%; 45.49%)
+ FoldScaleAxis: 7153us [3us] (54.51%; 54.51%)
+ FoldConstant: 7150us [1461us] (54.49%; 99.96%)
+ InferType: 5689us [5689us] (43.35%; 79.56%)
@@ -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: 6260us [6260us] (44.96%; 44.96%)
- FoldScaleAxis: 7665us [3us] (55.04%; 55.04%)
- FoldConstant: 7662us [1578us] (55.02%; 99.96%)
- InferType: 6084us [6084us] (43.69%; 79.40%)
+ InferType: 5766us [5766us] (44.65%; 44.65%)
+ FoldScaleAxis: 7148us [2us] (55.35%; 55.35%)
+ FoldConstant: 7146us [1497us] (55.33%; 99.98%)
+ InferType: 5648us [5648us] (43.74%; 79.04%)
@@ -404,7 +404,7 @@ profile result.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 c952f3af2..98544d9a9 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
@@ -295,11 +295,7 @@ latency of convolution.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
- Convolution: 54.164380 ms
+ Convolution: 37.543247 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 ff3488e62..46b7f1d00 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
@@ -628,11 +628,7 @@ be able to run on our build server
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
- conv2d with tensor core: 6.624399 ms
+ conv2d with tensor core: 7.344750 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 785d02af0..d656225d2 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,10 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019481
- /workspace/python/tvm/target/target.py:317: 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. "
- Baseline: 3.300680
+ Numpy running time: 0.018099
+ Baseline: 3.421486
@@ -212,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.331405
+ Opt1: 0.300247
@@ -311,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.345347
+ Opt2: 0.342873
@@ -403,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.134943
+ Opt3: 0.111848
@@ -522,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.112714
+ Opt4: 0.108546
@@ -640,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.114435
+ Opt5: 0.108801
@@ -761,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.147957
+ Opt6: 0.144627
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 33db6744c..474537d1f 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
=================
-**00:35.841** total execution time for **how_to_optimize_operators** files:
+**00:34.792** total execution time for **how_to_optimize_operators** files:
-- **00:33.115**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.448**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.279**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.307**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.295**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.190**: :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 e6ed68be3..1b025201e 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
=================
-**05:04.511** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:25.931**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:21.032**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:41.416**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:17.603**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:09.448**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:09.080**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**03:32.007** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **01:19.067**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **01:05.111**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **00:40.474**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:09.386**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.244**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.726**: :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 5c6be146b..fccf27da0 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
@@ -191,7 +191,6 @@ file and apply it.
-
We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.
@@ -223,675 +222,36 @@ cooperative fetching, unrolling and operator fusion.
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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 168), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 168), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 280), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 280), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 336), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 392), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 392), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 18), 81) < 72) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 2), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 560), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 616), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 616), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 24), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 672), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 728), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 728), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 784), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 840), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 840), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 896), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 896), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 952), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 952), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1064), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1120), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1120), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1176), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1176), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 17), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1232), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 8), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1288)] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
+ for (ff.outer.inner.init: int32, 0, 2) {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[ff.outer.inner.init] = 0f32
+ }
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_1, 56)) < 9), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + threadIdx.x_1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + threadIdx.x_1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused. [...]
+ }
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2 + 56))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 112), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 21), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 80), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 35), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 136), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 104), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 63), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 72), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 128), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 77), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 96), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 91), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 105), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 120), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 119), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 88), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 133), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 112), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 154), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 80), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 161), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 136), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 175), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 104), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 182), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 189), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 72), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 128), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 203), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 210), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 96), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 217), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 231), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 120), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 238), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 245), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 88), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 259), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 266), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 112), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 273), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 80), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[((((blockIdx.x*73728) + cse_var_1) + floormod((threadIdx.x_2 + 136), 144)) + 69120)]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((threadIdx.x_2 < 384), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 24)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + (ry.outer.outer*3)) + floormod(threadIdx.x_2, 3))]
}
- for (rc.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
+ for (rx.outer.inner: int32, 0, 3) {
+ for (ff.outer.inner: int32, 0, 2) {
+ for (rc.inner: int32, 0, 8) {
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((rc.inner*63) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*48) + (ff.outer.inner*24)) + (rc.inner*3)) + rx.outer.inner)]))
+ }
+ }
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner) + 392)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -944,11 +304,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
- Execution time of this operator: 0.163 ms
+ Execution time of this operator: 0.351 ms
@@ -993,35 +349,35 @@ 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=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=8)
- 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=2)
+ 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=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=4)
- 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=3)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ 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)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
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=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=8)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ 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=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)
@@ -1041,19 +397,17 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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)
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=56)
+ 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=392)
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=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=56)
+ 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=392)
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", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
- /workspace/python/tvm/target/target.py:317: 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. "
#ifdef _WIN32
using uint = unsigned int;
@@ -1068,607 +422,36 @@ 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__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
- conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((9 <= ((((int)threadIdx.x) + 6) % 81)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 81) * 49)) + ((((((int)threadIdx.x) + 6) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 504) / 81) * 49)) + (((((int)threadIdx.x) / 9) + 2) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + ((((((int)threadIdx.x) + 11) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 8) {
- pad_temp_shared[(((int)threadIdx.x) + 1288)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 56)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 80))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 136) % 144))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 48))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 16))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 72))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 40))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 64))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 120) % 144))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 32))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 88))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 56))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 80))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 136) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 48))];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 16))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 72))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 40))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 64))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 120) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 32))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 88))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2072) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 56))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 80))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 136)) + 69120)];
- }
- __syncthreads();
- 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 * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
+ extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[504];
+ __shared__ float kernel_shared[384];
+ for (int ff_outer_inner_init = 0; ff_outer_inner_init < 2; ++ff_outer_inner_init) {
+ conv2d_nchw[ff_outer_inner_init] = 0.000000e+00f;
+ }
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) / 56)) < 9) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x))] = (((((1 <= (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer)) && ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_ou [...]
+ }
+ }
+ if (((int)threadIdx.x) < 384) {
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ __syncthreads();
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((rc_inner * 63) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 48) + (ff_outer_inner * 24)) + (rc_inner * 3)) + rx_outer_inner)]));
+ }
+ }
+ }
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner) + 392)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1727,7 +510,7 @@ 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 25.931 seconds)
+ **Total running time of the script:** ( 1 minutes 5.111 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_arm.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_arm.rst.txt
index ef1f1cadd..9d51f1275 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_arm.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_arm.rst.txt
@@ -304,7 +304,7 @@ The task scheduler will just optimize this objective.
Get model...
Extract tasks...
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
========== Task 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 29c5e9c98..3b2642c9e 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
@@ -182,7 +182,7 @@ The task scheduler will just optimize this objective.
.. code-block:: none
Extract tasks...
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
========== Task 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 64], [1, 56, 56, 64]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -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)
- 9.7968 9.7873 9.8379 9.7650 0.0305
+ 9.8867 9.8886 9.9073 9.8642 0.0176
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt
index bdd155734..991105024 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt
@@ -207,7 +207,7 @@ The task scheduler will just optimize this objective.
.. code-block:: none
Extract tasks...
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
========== Task 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 3808fa44a..67ea5eccc 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
@@ -205,7 +205,7 @@ The task scheduler will just optimize this objective.
Get model...
Extract tasks...
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
========== Task 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -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)
- 764.5206 764.1332 765.3251 764.1035 0.5690
+ 807.9377 808.4186 809.2553 806.1391 1.3168
@@ -660,7 +660,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.032 seconds)
+ **Total running time of the script:** ( 1 minutes 19.067 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 0999bda0c..480d5eef1 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
@@ -330,7 +330,6 @@ file and apply it.
-
We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
layout transformation, parallelization, vectorization, unrolling, and operator fusion.
@@ -362,26 +361,78 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [128], [])[((i.inner.init*16) + j.init)] = 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])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_2: int32 = ((i.inner*16) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ 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
+ }
+ }
+ 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 + 1)
+ let cse_var_16: int32 = (cse_var_18 + 11)
+ let cse_var_15: int32 = (cse_var_18 + 12)
+ let cse_var_14: int32 = (cse_var_18 + 13)
+ let cse_var_13: int32 = (cse_var_18 + 14)
+ let cse_var_12: int32 = (cse_var_18 + 15)
+ let cse_var_11: int32 = (cse_var_18 + 2)
+ let cse_var_10: int32 = (cse_var_18 + 3)
+ let cse_var_9: int32 = (cse_var_18 + 4)
+ let cse_var_8: int32 = (cse_var_18 + 5)
+ let cse_var_7: int32 = (cse_var_18 + 6)
+ let cse_var_6: int32 = (cse_var_18 + 7)
+ let cse_var_5: int32 = (cse_var_18 + 8)
+ let cse_var_4: int32 = (cse_var_18 + 9)
+ let cse_var_3: int32 = (cse_var_18 + 10)
+ {
+ 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_17] = (compute_5[cse_var_17] + (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_11] = (compute_5[cse_var_11] + (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_10] = (compute_5[cse_var_10] + (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_9] = (compute_5[cse_var_9] + (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_8] = (compute_5[cse_var_8] + (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_7] = (compute_5[cse_var_7] + (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_6] = (compute_5[cse_var_6] + (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_5] = (compute_5[cse_var_5] + (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_4] = (compute_5[cse_var_4] + (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_3] = (compute_5[cse_var_3] + (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_16] = (compute_5[cse_var_16] + (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_15] = (compute_5[cse_var_15] + (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_14] = (compute_5[cse_var_14] + (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_13] = (compute_5[cse_var_13] + (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_12] = (compute_5[cse_var_12] + (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 (i0.inner: int32, 0, 8) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ 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))
}
}
}
@@ -435,9 +486,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
- Execution time of this operator: 1.528 ms
+ Execution time of this operator: 1.850 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 5b6418efa..01bb5c7ec 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
=================
-**00:45.182** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.748** total execution time for **how_to_tune_with_autotvm** files:
-- **00:44.238**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.246**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.234**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.233**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.231**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:45.949**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.209**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.198**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.196**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.196**: :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 106425f5b..d7a312de0 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
@@ -249,9 +249,9 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -372,9 +372,9 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -495,9 +495,9 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -618,9 +618,9 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -741,9 +741,9 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -859,15 +859,15 @@ 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: 43.22/43.22 result: MeasureResult(costs=(0.005356313578947369,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6191003322601318, timestamp=1653698537.7085912) [('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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 92.36/92.36 result: MeasureResult(costs=(0.002506575395833333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0522191524505615, timestamp=1653700071.3242364) [('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: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -983,14 +983,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1106,14 +1106,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/92.36 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
@@ -1247,14 +1247,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1370,14 +1370,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1493,14 +1493,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1616,14 +1616,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1739,14 +1739,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1862,14 +1862,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1985,14 +1985,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -2108,14 +2108,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -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: 0.00/43.22 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/92.36 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: 0x00007fbeb4255fa2
+ 12: 0x00007f6b81a8dfa2
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: 144.61/144.61 result: MeasureResult(costs=(0.0016009116000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4389643669128418, timestamp=1653698564.3018105) [('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: 143.87/143.87 result: MeasureResult(costs=(0.00160905357,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.412313461303711, timestamp=1653700090.8098168) [('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
@@ -2437,11 +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
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
- Time cost of this operator: 0.001958
+ Time cost of this operator: 0.002006
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_relay_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_relay_cuda.rst.txt
index 97f00428c..255ead941 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_relay_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_relay_cuda.rst.txt
@@ -164,7 +164,7 @@ Before tuning, we apply some configurations.
.. code-block:: none
- /workspace/python/tvm/target/target.py:370: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
+ /workspace/python/tvm/target/target.py:371: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
warnings.warn("Try specifying cuda arch by adding 'arch=sm_xx' to your target.")
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 0275bf24d..86e9bd3ba 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
@@ -289,15 +289,15 @@ Timing the untuned program
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
########## 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 310.2 98.732 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.981 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.902 0.287 (1, 1, 10, 10, 3) 1 1
- Total_time - 314.184 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.9 98.759 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.953 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 0.288 (1, 1, 10, 10, 3) 1 1
+ Total_time - 314.806 - - - -
@@ -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 219.2 98.647 (1, 1, 10, 10, 6) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.176 0.979 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.831 0.374 (1, 3, 10, 10, 1) 1 1
- Total_time - 222.207 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 195.7 98.729 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.72 0.868 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.8 0.404 (1, 3, 10, 10, 1) 1 1
+ Total_time - 198.22 - - - -
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 1b62e7b3a..847a74bd6 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:49.065** total execution time for **how_to_work_with_microtvm** files:
+**00:48.233** total execution time for **how_to_work_with_microtvm** files:
-- **00:44.479**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.950**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.213**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.212**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.212**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:44.180**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.494**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.193**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.184**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.181**: :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 2f76f92df..3ef5cc707 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
=================
-**00:12.028** total execution time for **how_to_work_with_relay** files:
+**00:05.299** total execution time for **how_to_work_with_relay** files:
-- **00:10.059**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.739**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.230**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:03.495**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.603**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.201**: :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_relay/using_external_lib.rst.txt b/docs/_sources/how_to/work_with_relay/using_external_lib.rst.txt
index 798efab3b..d998fc0ad 100644
--- a/docs/_sources/how_to/work_with_relay/using_external_lib.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/using_external_lib.rst.txt
@@ -108,7 +108,7 @@ By setting the logging level to DEBUG, the result of Relay graph compilation wil
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -547,7 +547,7 @@ To do that, all we need to do is to append the option " -libs=cudnn" to the targ
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/how_to/work_with_schedules/extern_op.rst.txt b/docs/_sources/how_to/work_with_schedules/extern_op.rst.txt
index f4e72ae2f..d063c4c2d 100644
--- a/docs/_sources/how_to/work_with_schedules/extern_op.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/extern_op.rst.txt
@@ -103,15 +103,6 @@ We can verify that the result matches what we expected.
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- /workspace/python/tvm/target/target.py:317: 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. "
-
Extern Contrib Wrappers
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index b3ab50bdc..b22d798f1 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -68,10 +68,6 @@ In the following example, we use :any:`tvm.tir.call_pure_extern` to call
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
#ifdef _WIN32
using uint = unsigned int;
@@ -136,8 +132,6 @@ The following code use te.exp instead, which create an intrinsic call
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
#ifdef _WIN32
using uint = unsigned int;
@@ -262,8 +256,6 @@ fast math version :code:`__expf`.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
#ifdef _WIN32
using uint = unsigned int;
@@ -344,8 +336,6 @@ The following example add an intrinsic :code:`mylog` to the system.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
#ifdef _WIN32
using uint = unsigned int;
diff --git a/docs/_sources/how_to/work_with_schedules/reduction.rst.txt b/docs/_sources/how_to/work_with_schedules/reduction.rst.txt
index d5869f7ba..9f4c358e0 100644
--- a/docs/_sources/how_to/work_with_schedules/reduction.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/reduction.rst.txt
@@ -329,10 +329,6 @@ columns by threadIdx.x and finally do a cross thread reduction over threadIdx.x
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
#if defined(__CUDA_ARCH__) && (__CUDA_ARCH__ < 700)
#define __shfl_sync(mask, var, lane, width) \
diff --git a/docs/_sources/how_to/work_with_schedules/scan.rst.txt b/docs/_sources/how_to/work_with_schedules/scan.rst.txt
index 65b17e0f5..9a56294bc 100644
--- a/docs/_sources/how_to/work_with_schedules/scan.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/scan.rst.txt
@@ -147,17 +147,6 @@ numpy to verify the correctness of the result.
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
-
Multi-Stage Scan Cell
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 3dae04a78..76c01bbb0 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
=================
-**00:05.885** total execution time for **how_to_work_with_schedules** files:
+**00:05.095** total execution time for **how_to_work_with_schedules** files:
-- **00:02.142**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.159**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.754**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.743**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.337**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.257**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.254**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.239**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:01.924**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:00.776**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.702**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.662**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.305**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.254**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.236**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:00.235**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.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 6b5dc5c21..4fc50c71a 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/tmpaeu1tnrm/input0.cc'\nsource_filename = \"/tmp/tmpaeu1tnrm/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/tmp8lr3zj54/input0.cc'\nsource_filename = \"/tmp/tmp8lr3zj54/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)
@@ -353,15 +353,6 @@ ensure our implementation is correct.
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- /workspace/python/tvm/target/target.py:317: 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. "
-
Reduce-update for Tensorize
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 2090de257..c4450800e 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
=================
-**00:22.062** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:19.852** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:21.841**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.221**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:19.668**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.183**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt
index 4630f4276..8fcff9f1a 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt
@@ -498,7 +498,7 @@ Finally, we launch tuning jobs and evaluate the end-to-end performance.
.. code-block:: none
Extract tasks...
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/workspace/python/tvm/target/target.py:255: 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. "
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 4fb0b408f..e4c641c4d 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -261,13 +261,13 @@ The compilation steps are:
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/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,
/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 22.99s!
+ resnet18_v1 inference graph built in 21.38s!
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 8863ebfff..a7e944edd 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -299,11 +299,11 @@ The compilation steps are:
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/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 15.93s!
+ yolov3-tiny inference graph built in 14.83s!
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 be2872538..9d67ffa8f 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
=================
-**01:31.442** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.066** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:48.157**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:43.285**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.711**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.355**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
diff --git a/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt b/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt
index fa873ea12..4e91b3a43 100644
--- a/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt
@@ -616,7 +616,7 @@ into a TVM function.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
index ab1e14c0a..0c8bb315f 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
@@ -880,7 +880,7 @@ ensure correctness.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
Execution statistics:
inp_load_nbytes : 114688
diff --git a/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
index 1a5a30dfd..aa9a6edfe 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
@@ -653,7 +653,7 @@ ensure correctness.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
Execution statistics:
inp_load_nbytes : 4096
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 7c7192b00..cc2e0dd87 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
=================
-**00:03.685** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.510** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.107**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.578**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.999**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.510**: :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 4b83cda75..1721826b1 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
=================
-**00:01.037** total execution time for **topic_vta_tutorials** files:
+**00:00.949** total execution time for **topic_vta_tutorials** files:
-- **00:00.526**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.512**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.487**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.462**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt b/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
index 63810c71d..47f70a28b 100644
--- a/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
@@ -487,7 +487,7 @@ we want to compile to.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 86ae7cf56..f66cee8a6 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -184,8 +184,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
-
-
+ *E*E*E
@@ -306,9 +305,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
- Execution time of this operator: 95.226 ms
+ Execution time of this operator: 93.881 ms
@@ -404,7 +401,7 @@ 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)
-
+ *E
@@ -417,6 +414,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 29.051 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index bf47a382b..0e9fa028f 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -432,15 +432,6 @@ best config with the same argument.
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- /workspace/python/tvm/target/target.py:317: 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. "
-
Final Notes and Summary
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index cdcb0f5db..c1efb5e59 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -212,7 +212,7 @@ runtime module from the library.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -280,7 +280,7 @@ standard deviation.
.. code-block:: none
- {'mean': 500.36660102999804, 'median': 500.2719358000036, 'std': 0.8369663214375898}
+ {'mean': 492.5187951512635, 'median': 492.40721066016704, 'std': 1.1536713822642573}
@@ -494,31 +494,29 @@ 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: 17.37/ 17.37 GFLOPS | Progress: (4/20) | 6.04 s
[Task 1/25] Current/Best: 6.14/ 17.37 GFLOPS | Progress: (8/20) | 9.01 s
[Task 1/25] Current/Best: 11.50/ 22.63 GFLOPS | Progress: (12/20) | 11.47 s
[Task 1/25] Current/Best: 16.59/ 22.63 GFLOPS | Progress: (16/20) | 13.16 s
[Task 1/25] Current/Best: 11.56/ 23.80 GFLOPS | Progress: (20/20) | 14.91 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.24/ 13.21 GFLOPS | Progress: (4/20) | 3.67 s
[Task 2/25] Current/Best: 14.11/ 18.06 GFLOPS | Progress: (8/20) | 4.97 s
[Task 2/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (12/20) | 6.31 s
[Task 2/25] Current/Best: 12.27/ 21.10 GFLOPS | Progress: (16/20) | 7.61 s
[Task 2/25] Current/Best: 19.51/ 21.10 GFLOPS | Progress: (20/20) | 9.23 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/ 10.39 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.50/ 16.84 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 14.32/ 16.84 GFLOPS | Progress: (12/20) | 9.53 s
[Task 3/25] Current/Best: 7.16/ 23.58 GFLOPS | Progress: (16/20) | 11.47 s
[Task 3/25] Current/Best: 12.50/ 23.58 GFLOPS | Progress: (20/20) | 15.99 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.40/ 19.10 GFLOPS | Progress: (4/20) | 2.37 s
[Task 4/25] Current/Best: 6.54/ 19.10 GFLOPS | Progress: (8/20) | 6.78 s
[Task 4/25] Current/Best: 21.49/ 21.49 GFLOPS | Progress: (12/20) | 11.33 s
[Task 4/25] Current/Best: 17.25/ 21.49 GFLOPS | Progress: (16/20) | 13.59 s
[Task 4/25] Current/Best: 13.00/ 21.49 GFLOPS | Progress: (20/20) | 15.62 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.67/ 10.08 GFLOPS | Progress: (4/20) | 2.54 s
[Task 5/25] Current/Best: 11.69/ 12.76 GFLOPS | Progress: (8/20) | 4.60 s
[Task 5/25] Current/Best: 9.74/ 17.99 GFLOPS | Progress: (12/20) | 7.69 s
[Task 5/25] Current/Best: 11.65/ 22.40 GFLOPS | Progress: (16/20) | 9.11 s
[Task 5/25] Current/Best: 11.62/ 22.40 GFLOPS | Progress: (20/20) | 10.99 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.28/ 20.61 GFLOPS | Progress: (4/20) | 3.97 s
[Task 6/25] Current/Best: 18.84/ 20.61 GFLOPS | Progress: (8/20) | 5.72 s
[Task 6/25] Current/Best: 13.08/ 20.61 GFLOPS | Progress: (12/20) | 7.64 s
[Task 6/25] Current/Best: 19.74/ 20.61 GFLOPS | Progress: (16/20) | 9.89 s
[Task 6/25] Current/Best: 3.72/ 20.61 GFLOPS | Progress: (20/20) | 12.39 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.90/ 12.17 GFLOPS | Progress: (4/20) | 3.61 s
[Task 7/25] Current/Best: 19.84/ 21.04 GFLOPS | Progress: (8/20) | 5.12 s
[Task 7/25] Current/Best: 15.44/ 21.04 GFLOPS | Progress: (12/20) | 7.03 s
[Task 7/25] Current/Best: 12.22/ 21.04 GFLOPS | Progress: (16/20) | 9.08 s
[Task 7/25] Current/Best: 6.46/ 21.54 GFLOPS | Progress: (20/20) | 11.53 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.39/ 14.49 GFLOPS | Progress: (4/20) | 2.89 s
[Task 8/25] Current/Best: 9.82/ 14.49 GFLOPS | Progress: (8/20) | 7.72 s
[Task 8/25] Current/Best: 12.83/ 14.49 GFLOPS | Progress: (12/20) | 14.04 s
[Task 8/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (16/20) | 16.13 s
[Task 8/25] Current/Best: 20.10/ 20.10 GFLOPS | Progress: (20/20) | 22.80 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.08/ 15.77 GFLOPS | Progress: (4/20) | 11.93 s
[Task 9/25] Current/Best: 22.79/ 22.79 GFLOPS | Progress: (8/20) | 13.68 s
[Task 9/25] Current/Best: 8.24/ 22.79 GFLOPS | Progress: (12/20) | 16.06 s
[Task 9/25] Current/Best: 17.82/ 22.79 GFLOPS | Progress: (16/20) | 18.69 s
[Task 9/25] Current/Best: 8.92/ 22.79 GFLOPS | Progress: (20/20) | 26.60 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.00/ 18.00 GFLOPS | Progress: (4/20) | 2.54 s
[Task 10/25] Current/Best: 15.43/ 18.00 GFLOPS | Progress: (8/20) | 4.12 s
[Task 10/25] Current/Best: 12.85/ 19.09 GFLOPS | Progress: (12/20) | 5.64 s
[Task 10/25] Current/Best: 19.16/ 20.57 GFLOPS | Progress: (16/20) | 6.75 s
[Task 10/25] Current/Best: 8.94/ 20.57 GFLOPS | Progress: (20/20
) | 8.27 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.12/ 18.04 GFLOPS | Progress: (4/20) | 3.25 s
[Task 11/25] Current/Best: 16.83/ 18.04 GFLOPS | Progress: (8/20) | 5.98 s
[Task 11/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (12/20) | 8.00 s
[Task 11/25] Current/Best: 13.33/ 21.08 GFLOPS | Progress: (16/20) | 10.82 s
[Task 11/25] Current/Best: 19.39/ 21.53 GFLOPS | Progress: (20/20) | 12.87 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.77/ 18.22 GFLOPS | Progress: (4/20) | 5.31 s
[Task 12/25] Current/Best: 5.28/ 18.22 GFLOPS | Progress: (8/20) | 9.05 s
[Task 12/25] Current/Best: 19.19/ 19.19 GFLOPS | Progress: (12/20) | 11.01 s
[Task 12/25] Current/Best: 14.11/ 19.19 GFLOPS | Progress: (16/20) | 13.80 s
[Task 12/25] Current/Best: 15.21/ 19.19 GFLOPS | Progress: (20/20) | 15.75 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.23/ 17.29 GFLOPS | Progress: (4/20) | 3.65 s
[Task 13/25] Current/Best: 15.80/ 20.80 GFLOPS | Progress: (8/20) | 6.12 s
[Task 13/25] Current/Best: 19.45/ 21.49 GFLOPS | Progress: (12/20) | 9.01 s
[Task 13/25] Current/Best: 12.22/ 21.49 GFLOPS | Progress: (16/20) | 12.41 s
[Task 13/25] Current/Best: 18.65/ 21.49 GFLOPS | Progress: (20/20) | 14.62 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.62/ 13.62 GFLOPS | Progress: (4/20) | 3.24 s
[Task 14/25] Current/Best: 6.11/ 13.62 GFLOPS | Progress: (8/20) | 5.46 s
[Task 14/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (12/20) | 8.04 s
[Task 14/25] Current/Best: 14.91/ 20.51 GFLOPS | Progress: (16/20) | 9.92 s Done.
-
[Task 14/25] Current/Best: 17.01/ 20.51 GFLOPS | Progress: (20/20) | 11.64 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.08/ 17.56 GFLOPS | Progress: (4/20) | 2.66 s
[Task 15/25] Current/Best: 14.39/ 17.86 GFLOPS | Progress: (8/20) | 4.19 s
[Task 15/25] Current/Best: 10.34/ 22.06 GFLOPS | Progress: (12/20) | 6.44 s
[Task 15/25] Current/Best: 20.24/ 22.06 GFLOPS | Progress: (16/20) | 9.51 s
[Task 15/25] Current/Best: 9.64/ 22.06 GFLOPS | Progress: (20/20) | 10.71 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.17/ 20.17 GFLOPS | Progress: (4/20) | 2.96 s
[Task 16/25] Current/Best: 3.03/ 20.17 GFLOPS | Progress: (8/20) | 4.58 s
[Task 16/25] Current/Best: 19.40/ 20.17 GFLOPS | Progress: (12/20) | 5.80 s
[Task 16/25] Current/Best: 17.71/ 20.17 GFLOPS | Progress: (16/20) |
7.19 s
[Task 16/25] Current/Best: 9.95/ 21.80 GFLOPS | Progress: (20/20) | 9.26 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.12/ 18.71 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 14.19/ 22.98 GFLOPS | Progress: (8/20) | 7.59 s
[Task 17/25] Current/Best: 18.18/ 22.98 GFLOPS | Progress: (12/20) | 9.64 s
[Task 17/25] Current/Best: 16.43/ 22.98 GFLOPS | Progress: (16/20) | 11.79 s
[Task 17/25] Current/Best: 10.03/ 22.98 GFLOPS | Progress: (20/20) | 13.93 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.29/ 17.74 GFLOPS | Progress: (4/20) | 3.70 s
[Task 18/25] Current/Best: 10.54/ 17.74 GFLOPS | Progress: (8/20) | 7.25 s
[Task 18/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 9.19 s
[Task 18/25] Current/Best: 9.85/ 18.91 GFLOPS | Progress: (16/20) | 12.81 s
[Task 18/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (20/20) | 14.34 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.04/ 20.21 GFLOPS | Progress: (4/20) | 6.21 s
[Task 19/25] Current/Best: 2.61/ 20.21 GFLOPS | Progress: (8/20) | 9.48 s
[Task 19/25] Current/Best: 17.89/ 20.65 GFLOPS | Progress: (12/20) | 12.33 s
[Task 19/25] Current/Best: 13.97/ 21.58 GFLOPS | Progress: (16/20) | 15.17 s
[Task 19/25] Current/Best: 2.70/ 22.94 GFLOPS | Progress: (20/20) | 17.94 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.30/ 15.04 GFLOPS | Progress: (4/20) | 3.29 s Done.
- Done.
-
[Task 20/25] Current/Best: 10.10/ 15.04 GFLOPS | Progress: (8/20) | 6.78 s
[Task 20/25] Current/Best: 2.32/ 16.54 GFLOPS | Progress: (12/20) | 10.78 s
[Task 20/25] Current/Best: 12.39/ 16.54 GFLOPS | Progress: (16/20) | 14.61 s
[Task 20/25] Current/Best: 13.31/ 21.59 GFLOPS | Progress: (20/20) | 16.72 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.54 GFLOPS | Progress: (4/20) | 3.21 s
[Task 21/25] Current/Best: 14.40/ 17.54 GFLOPS | Progress: (8/20) | 4.82 s
[Task 21/25] Current/Best: 1.61/ 17.54 GFLOPS | Progress: (12/20) | 6.95 s
[Task 21/25] Current/Best: 17.03/ 17.54 GFLOPS | Progress: (16/20) | 10.42 s
[Task 21/25] Current/Best: 4.46/ 17.54 GFLOPS | Progress: (20/20) | 17.81 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.96 GFLOPS | Progress: (4/20
) | 2.66 s
[Task 22/25] Current/Best: 9.11/ 21.34 GFLOPS | Progress: (8/20) | 4.57 s
[Task 22/25] Current/Best: 19.65/ 21.34 GFLOPS | Progress: (12/20) | 6.89 s
[Task 22/25] Current/Best: 15.21/ 21.34 GFLOPS | Progress: (16/20) | 8.95 s
[Task 22/25] Current/Best: 14.73/ 21.34 GFLOPS | Progress: (20/20) | 10.71 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.32/ 19.89 GFLOPS | Progress: (4/20) | 3.27 s
[Task 23/25] Current/Best: 15.81/ 19.89 GFLOPS | Progress: (8/20) | 6.66 s
[Task 23/25] Current/Best: 20.71/ 21.14 GFLOPS | Progress: (12/20) | 8.52 s
[Task 23/25] Current/Best: 5.57/ 21.14 GFLOPS | Progress: (16/20) | 15.68 s
[Task 23/25] Current/Best: 7.25/ 21.14 GFLOPS | Progress: (20/20) | 19.97 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.60/ 8.60 GFLOPS | Progress: (4/20) | 11.78 s
[Task 24/25] Current/Best: 1.89/ 8.60 GFLOPS | Progress: (8/20) | 22.77 s
[Task 24/25] Current/Best: 3.78/ 8.60 GFLOPS | Progress: (12/20) | 34.28 s Done.
- Done.
-
[Task 24/25] Current/Best: 7.33/ 8.60 GFLOPS | Progress: (16/20) | 39.88 s
[Task 24/25] Current/Best: 3.18/ 8.91 GFLOPS | Progress: (20/20) | 45.90 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 2.80 GFLOPS | Progress: (4/20) | 11.59 s
[Task 25/25] Current/Best: 5.21/ 7.49 GFLOPS | Progress: (8/20) | 22.86 s
[Task 25/25] Current/Best: 5.80/ 7.49 GFLOPS | Progress: (12/20) | 34.15 s
[Task 25/25] Current/Best: 5.53/ 8.65 GFLOPS | Progress: (16/20) | 35.92 s
[Task 25/25] Current/Best: 2.88/ 8.65 GFLOPS | Progress: (20/20) | 46.63 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 16.85/ 22.89 GFLOPS | Progress: (16/20) | 13.68 s
[Task 1/25] Current/Best: 11.64/ 23.94 GFLOPS | Progress: (20/20) | 15.83 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.84/ 21.46 GFLOPS | Progress: (16/20) | 8.72 s
[Task 2/25] Current/Best: 20.08/ 21.46 GFLOPS | Progress: (20/20) | 10.18 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 7.22/ 23.78 GFLOPS | Progress: (16/20) | 10.53 s
[Task 3/25] Current/Best: 12.67/ 23.78 GFLOPS | Progress: (20/20) | 14.92 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 17.37/ 21.99 GFLOPS | Progress: (16/20) | 8.87 s
[Task 4/25] Current/Best: 13.49/ 21.99 GFLOPS | Progress: (20/20) | 10.70 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.77/ 23.04 GFLOPS | Progress: (16/20) | 7.81 s
[Task 5/25] Current/Best: 12.08/ 23.04 GFLOPS | Progress: (20/20) | 9.40 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 19.94/ 20.90 GFLOPS | Progress: (16/20) | 8.44 s
[Task 6/25] Current/Best: 3.69/ 20.90 GFLOPS | Progress: (20/20) | 10.89 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.30/ 21.22 GFLOPS | Progress: (16/20) | 8.08 s
[Task 7/25] Current/Best: 6.40/ 21.73 GFLOPS | Progress: (20/20) | 10.45 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (16/20) | 12.32 s
[Task 8/25] Current/Best: 19.87/ 19.87 GFLOPS | Progress: (20/20) | 18.73 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 18.07/ 23.11 GFLOPS | Progress: (16/20) | 15.02 s
[Task 9/25] Current/Best: 9.09/ 23.11 GFLOPS | Progress: (20/20) | 22.59 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 10/25] Current/Best: 19.22/ 20.63 GFLOPS | Progress: (16/20) | 6.18 s
[Task 10/25] Current/Best: 8.98/ 20.63 GFLOPS | Progress: (20/20) | 7.64 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 13.57/ 21.18 GFLOPS | Progress: (16/20) | 8.77 s
[Task 11/25] Current/Best: 19.52/ 21.50 GFLOPS | Progress: (20/20) | 10.72 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.33/ 19.11 GFLOPS | Progress: (16/20) | 10.11 s
[Task 12/25] Current/Best: 15.21/ 19.11 GFLOPS | Progress: (20/20) | 11.98 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.31/ 21.81 GFLOPS | Progress: (16/20) | 8.90 s
[Task 13/25] Current/Best: 18.73/ 21.81 GFLOPS | Progress: (20/20) | 11.05 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 17.03/ 19.90 GFLOPS | Progress: (16/20) | 8.06 s
[Task 14/25] Current/Best: 17.19/ 19.90 GFLOPS | Progress: (20/20) | 9.45 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 15/25] Current/Best: 20.35/ 22.39 GFLOPS | Progress: (16/20) | 6.21 s
[Task 15/25] Current/Best: 9.72/ 22.39 GFLOPS | Progress: (20/20) | 7.26 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 18.41/ 20.61 GFLOPS | Progress: (16/20) | 6.35 s
[Task 16/25] Current/Best: 10.00/ 22.53 GFLOPS | Progress: (20/20) | 8.30 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 16.53/ 23.46 GFLOPS | Progress: (16/20) | 9.42 s
[Task 17/25] Current/Best: 10.06/ 23.46 GFLOPS | Progress: (20/20) | 11.44 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.06/ 19.45 GFLOPS | Progress: (16/20) | 9.32 s
[Task 18/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (20/20) | 10.76 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 14.42/ 22.06 GFLOPS | Progress: (16/20) | 11.55 s
[Task 19/25] Current/Best: 2.71/ 23.90 GFLOPS | Progress: (20/20) | 14.21 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 12.26/ 16.65 GFLOPS | Progress: (16/20) | 10.69 s
[Task 20/25] Current/Best: 12.55/ 22.39 GFLOPS | Progress: (20/20) | 12.68 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 21/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 7.46 s
[Task 21/25] Current/Best: 4.47/ 18.28 GFLOPS | Progress: (20/20) | 14.43 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.67/ 22.10 GFLOPS | Progress: (16/20) | 7.14 s
[Task 22/25] Current/Best: 14.56/ 22.10 GFLOPS | Progress: (20/20) | 8.74 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.44/ 21.95 GFLOPS | Progress: (16/20) | 13.34 s
[Task 23/25] Current/Best: 7.80/ 21.95 GFLOPS | Progress: (20/20) | 17.42 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.83/ 8.81 GFLOPS | Progress: (16/20) | 13.82 s
[Task 24/25] Current/Best: 3.32/ 8.81 GFLOPS | Progress: (20/20) | 19.55 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.76/ 8.35 GFLOPS | Progress: (16/20) | 13.53 s
[Task 25/25] Current/Best: 2.85/ 9.15 GFLOPS | Progress: (20/20) | 24.19 s
The output from this tuning process will look something like this:
@@ -660,8 +658,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 416.879001669995, 'median': 413.8142585999958, 'std': 9.18739572704193}
- unoptimized: {'mean': 500.36660102999804, 'median': 500.2719358000036, 'std': 0.8369663214375898}
+ optimized: {'mean': 408.95329352933913, 'median': 408.035372197628, 'std': 3.4917680862039147}
+ unoptimized: {'mean': 492.5187951512635, 'median': 492.40721066016704, 'std': 1.1536713822642573}
@@ -681,7 +679,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 23.069 seconds)
+ **Total running time of the script:** ( 8 minutes 30.128 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 68539b759..dea2cde64 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -129,15 +129,6 @@ on our webpage building server. See the detailed note in the following block.
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- /workspace/python/tvm/target/target.py:317: 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. "
-
.. note::
@@ -244,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.239e-07 secs/op
+ 1.304e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 654ddc29b..90e0d8645 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -185,7 +185,7 @@ we can schedule the following series of operations ending with :code:`topi.sum`
.. code-block:: none
- /workspace/python/tvm/target/target.py:370: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
+ /workspace/python/tvm/target/target.py:371: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
warnings.warn("Try specifying cuda arch by adding 'arch=sm_xx' to your target.")
@main = primfn(a_1: handle, b_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
@@ -233,7 +233,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x21e1d7f0)), stage(b, placeholder(b, 0x11af1890)), 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, 0xcd2e220)), stage(b, placeholder(b, 0x20545d50)), 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(min [...]
@@ -258,17 +258,6 @@ We can test the correctness by comparing with :code:`numpy` result as follows
-.. rst-class:: sphx-glr-script-out
-
- Out:
-
- .. code-block:: none
-
- /workspace/python/tvm/target/target.py:317: 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. "
- /workspace/python/tvm/target/target.py:317: 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. "
-
TOPI also provides common neural nets operations such as _softmax_ with optimized schedule
diff --git a/docs/_sources/tutorial/relay_quick_start.rst.txt b/docs/_sources/tutorial/relay_quick_start.rst.txt
index c0a988650..69d5f5720 100644
--- a/docs/_sources/tutorial/relay_quick_start.rst.txt
+++ b/docs/_sources/tutorial/relay_quick_start.rst.txt
@@ -226,9 +226,9 @@ in this example. Then the machine code will be generated as the module library.
.. code-block:: none
- /workspace/python/tvm/target/target.py:370: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
+ /workspace/python/tvm/target/target.py:371: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
warnings.warn("Try specifying cuda arch by adding 'arch=sm_xx' to your target.")
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 56fd63f24..c17d5ba1e 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
=================
-**13:01.385** total execution time for **tutorial** files:
+**11:53.332** total execution time for **tutorial** files:
-- **10:23.069**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:00.389**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:44.067**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:27.309**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:24.783**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:00.737**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.590**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.221**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.056**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.055**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **08:30.128**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:29.051**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **01:01.665**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:26.233**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:24.638**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.693**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.561**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.210**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.042**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.040**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.037**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.034**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 6a538d2d0..4487841cd 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -171,7 +171,7 @@ the inputs and outputs) as well as target language we want to compile to.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -253,7 +253,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000008
- naive: 0.000007
+ naive: 0.000006
@@ -397,7 +397,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000027
+ vector: 0.000026
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -447,10 +447,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.202120002351875e-06 1.0
- naive 6.845e-06 0.834540338112252
- parallel 6.3488e-06 0.7740437835802872
- vector 2.7318700000000003e-05 3.3306876749141248
+ numpy 8.175317198038101e-06 1.0
+ naive 5.8852e-06 0.7198742088456604
+ parallel 6.154400000000001e-06 0.7528025948004712
+ vector 2.55029e-05 3.1194997554492616
@@ -839,7 +839,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019133
+ Numpy running time: 0.018901
@@ -895,9 +895,9 @@ optimizations.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 3.283376
+ none: 3.463356
@@ -996,7 +996,7 @@ schedule.
.. code-block:: none
- blocking: 0.336531
+ blocking: 0.307851
@@ -1088,7 +1088,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.367043
+ vectorization: 0.340987
@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: 0.133959
+ loop permutation: 0.114636
@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: 0.110019
+ array packing: 0.108361
@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: 0.112716
+ block caching: 0.110529
@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: 0.146847
+ parallelization: 0.144460
@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 3.2833758305000003 1.0
- blocking 0.3365313444 0.10249552953210117
- vectorization 0.36704253490000005 0.11178815763046716
- loop permutation 0.13395941719999999 0.040799294419975166
- array packing 0.11001867749999998 0.03350779294834672
- block caching 0.11271634529999999 0.03432940702460957
- parallelization 0.14684703500000001 0.04472440639780119
+ none 3.4633562125 1.0
+ blocking 0.30785147679999997 0.08888819339139807
+ vectorization 0.3409873907 0.09845576653920349
+ loop permutation 0.1146356359 0.03309957996415594
+ array packing 0.1083608213 0.03128780715910838
+ block caching 0.1105286373 0.03191373642164739
+ parallelization 0.1444602083 0.04171104542426561
@@ -1554,7 +1554,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.389 seconds)
+ **Total running time of the script:** ( 1 minutes 1.665 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/_sources/tutorial/tensor_ir_blitz_course.rst.txt b/docs/_sources/tutorial/tensor_ir_blitz_course.rst.txt
index a4d50b1af..f2b6b727e 100644
--- a/docs/_sources/tutorial/tensor_ir_blitz_course.rst.txt
+++ b/docs/_sources/tutorial/tensor_ir_blitz_course.rst.txt
@@ -195,8 +195,6 @@ We can build the IRModule into a runnable module with specific target backends.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
<class 'tvm.driver.build_module.OperatorModule'>
@@ -422,8 +420,6 @@ After binding the threads, now build the IRModule with :code:`cuda` backends.
.. code-block:: none
- /workspace/python/tvm/target/target.py:317: 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. "
[0. 1. 2. 3. 4. 5. 6. 7.]
[1. 2. 3. 4. 5. 6. 7. 8.]
diff --git a/docs/commit_hash b/docs/commit_hash
index 600b2c548..d40bc7651 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-80d9549190b60a9d36ef93e6d842de26515d6718
+afb67e64a1891e1d1aab03c4614fca11473e7b27
diff --git a/docs/how_to/compile_models/from_coreml.html b/docs/how_to/compile_models/from_coreml.html
index 17703d4bd..cd2ae8d05 100644
--- a/docs/how_to/compile_models/from_coreml.html
+++ b/docs/how_to/compile_models/from_coreml.html
@@ -399,7 +399,7 @@ provided by apple in this example</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 3e99f9a95..b9830f08c 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -434,7 +434,7 @@ pip install opencv-python
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Compiling the model...
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index c9040a8e9..72b25ae1f 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.zipd8f044fe-824c-41a8-8070-245e5b9649de 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.zipf9610e5c-542d-4ecc-9997-c78b02f2b607 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
@@ -425,7 +425,7 @@ We support MXNet static graph(symbol) and HybridBlock in mxnet.gluon</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index 34c53f6f9..0e117e795 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,41 +406,42 @@ 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<07:22, 98.2kB/s]
- 0%| | 48.0k/41.5M [00:00<04:39, 155kB/s]
- 0%| | 96.0k/41.5M [00:00<03:18, 218kB/s]
- 0%| | 192k/41.5M [00:00<01:59, 364kB/s]
- 1%| | 392k/41.5M [00:00<01:04, 673kB/s]
- 2%|1 | 656k/41.5M [00:01<00:43, 992kB/s]
- 3%|3 | 1.29M/41.5M [00:01<00:21, 1.99MB/s]
- 6%|5 | 2.47M/41.5M [00:01<00:11, 3.71MB/s]
- 10%|9 | 3.96M/41.5M [00:01<00:07, 5.46MB/s]
- 13%|#3 | 5.45M/41.5M [00:01<00:05, 6.64MB/s]
- 17%|#6 | 6.93M/41.5M [00:01<00:04, 7.45MB/s]
- 20%|## | 8.41M/41.5M [00:02<00:04, 8.00MB/s]
- 24%|##3 | 9.90M/41.5M [00:02<00:03, 8.39MB/s]
- 27%|##7 | 11.4M/41.5M [00:02<00:03, 8.65MB/s]
- 31%|### | 12.9M/41.5M [00:02<00:03, 8.83MB/s]
- 35%|###4 | 14.3M/41.5M [00:02<00:03, 8.96MB/s]
- 38%|###8 | 15.8M/41.5M [00:02<00:02, 9.05MB/s]
- 42%|####1 | 17.3M/41.5M [00:03<00:02, 9.12MB/s]
- 45%|####5 | 18.8M/41.5M [00:03<00:02, 9.15MB/s]
- 49%|####8 | 20.3M/41.5M [00:03<00:02, 9.19MB/s]
- 52%|#####2 | 21.8M/41.5M [00:03<00:02, 9.22MB/s]
- 56%|#####6 | 23.2M/41.5M [00:03<00:02, 9.23MB/s]
- 60%|#####9 | 24.7M/41.5M [00:03<00:01, 9.25MB/s]
- 63%|######3 | 26.2M/41.5M [00:04<00:01, 9.26MB/s]
- 67%|######6 | 27.7M/41.5M [00:04<00:01, 9.26MB/s]
- 70%|####### | 29.2M/41.5M [00:04<00:01, 9.27MB/s]
- 74%|#######3 | 30.7M/41.5M [00:04<00:01, 9.27MB/s]
- 78%|#######7 | 32.2M/41.5M [00:04<00:01, 9.29MB/s]
- 81%|########1 | 33.6M/41.5M [00:04<00:00, 9.27MB/s]
- 85%|########4 | 35.1M/41.5M [00:05<00:00, 9.27MB/s]
- 88%|########8 | 36.6M/41.5M [00:05<00:00, 9.27MB/s]
- 92%|#########1| 38.1M/41.5M [00:05<00:00, 9.27MB/s]
- 95%|#########5| 39.6M/41.5M [00:05<00:00, 9.27MB/s]
- 99%|#########8| 41.1M/41.5M [00:05<00:00, 9.27MB/s]
-100%|##########| 41.5M/41.5M [00:05<00:00, 7.62MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:54, 91.7kB/s]
+ 0%| | 48.0k/41.5M [00:00<04:59, 145kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:32, 204kB/s]
+ 0%| | 168k/41.5M [00:00<02:31, 285kB/s]
+ 1%| | 336k/41.5M [00:00<01:21, 528kB/s]
+ 2%|1 | 680k/41.5M [00:01<00:42, 1.01MB/s]
+ 3%|3 | 1.34M/41.5M [00:01<00:21, 1.96MB/s]
+ 6%|6 | 2.68M/41.5M [00:01<00:10, 3.83MB/s]
+ 10%|9 | 4.15M/41.5M [00:01<00:07, 5.31MB/s]
+ 14%|#3 | 5.61M/41.5M [00:01<00:05, 6.30MB/s]
+ 17%|#7 | 7.09M/41.5M [00:01<00:05, 7.01MB/s]
+ 21%|## | 8.55M/41.5M [00:02<00:04, 7.48MB/s]
+ 24%|##4 | 10.0M/41.5M [00:02<00:03, 8.99MB/s]
+ 28%|##7 | 11.5M/41.5M [00:02<00:03, 9.56MB/s]
+ 30%|### | 12.5M/41.5M [00:02<00:03, 9.18MB/s]
+ 32%|###2 | 13.4M/41.5M [00:02<00:03, 7.89MB/s]
+ 35%|###4 | 14.4M/41.5M [00:02<00:03, 7.36MB/s]
+ 38%|###8 | 15.9M/41.5M [00:03<00:03, 7.75MB/s]
+ 42%|####1 | 17.4M/41.5M [00:03<00:03, 8.01MB/s]
+ 45%|####5 | 18.8M/41.5M [00:03<00:02, 8.19MB/s]
+ 49%|####8 | 20.3M/41.5M [00:03<00:02, 8.30MB/s]
+ 52%|#####2 | 21.8M/41.5M [00:03<00:02, 8.38MB/s]
+ 56%|#####6 | 23.2M/41.5M [00:03<00:02, 8.43MB/s]
+ 60%|#####9 | 24.7M/41.5M [00:04<00:02, 8.47MB/s]
+ 63%|######3 | 26.2M/41.5M [00:04<00:01, 8.50MB/s]
+ 67%|######6 | 27.6M/41.5M [00:04<00:01, 8.52MB/s]
+ 70%|####### | 29.1M/41.5M [00:04<00:01, 8.54MB/s]
+ 74%|#######3 | 30.6M/41.5M [00:04<00:01, 8.55MB/s]
+ 77%|#######7 | 32.1M/41.5M [00:05<00:01, 8.55MB/s]
+ 81%|######## | 33.5M/41.5M [00:05<00:00, 8.56MB/s]
+ 84%|########4 | 35.0M/41.5M [00:05<00:00, 8.56MB/s]
+ 88%|########7 | 36.5M/41.5M [00:05<00:00, 8.56MB/s]
+ 91%|#########1| 37.9M/41.5M [00:05<00:00, 8.56MB/s]
+ 95%|#########4| 39.4M/41.5M [00:05<00:00, 8.55MB/s]
+ 98%|#########8| 40.9M/41.5M [00:06<00:00, 9.79MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 7.11MB/s]
</pre></div>
</div>
</div>
@@ -499,7 +500,7 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_onnx.html b/docs/how_to/compile_models/from_onnx.html
index 2339a584a..b6e213f0f 100644
--- a/docs/how_to/compile_models/from_onnx.html
+++ b/docs/how_to/compile_models/from_onnx.html
@@ -424,7 +424,7 @@ provides a static definition of the input size.</p>
==> Context: Bad node spec for node. Name: OpType: Conv
warnings.warn(str(e))
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 0191b9153..32b0039db 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -433,7 +433,7 @@ A quick solution is</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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 8.803 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.684 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 afb9eb75a..9f1bcb1e0 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,8 +387,9 @@ 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]
- 43%|####3 | 19.3M/44.7M [00:00<00:00, 202MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 236MB/s]
+ 39%|###8 | 17.3M/44.7M [00:00<00:00, 182MB/s]
+ 98%|#########7| 43.8M/44.7M [00:00<00:00, 238MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 230MB/s]
</pre></div>
</div>
</div>
@@ -436,7 +437,7 @@ be unstable.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index d3f3641e1..6ba0c2d50 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -500,7 +500,7 @@ lib: target library which can be deployed on target with TVM runtime.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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 3.015 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.097 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/from_tflite.html b/docs/how_to/compile_models/from_tflite.html
index 10e76f74c..3f584b25f 100644
--- a/docs/how_to/compile_models/from_tflite.html
+++ b/docs/how_to/compile_models/from_tflite.html
@@ -467,7 +467,7 @@ flatc --python schema.fbs
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index f0a3f024c..974907074 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>05:28.091</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:20.996</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:08.803</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>01:03.015</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>00:58.727</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>00:31.632</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>00:24.481</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>00:22.662</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>00:22.627</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>00:19.584</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>00:14.027</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>00:02.533</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>01:09.684</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>01:03.097</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>00:58.035</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>00:29.793</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>00:25.065</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>00:21.155</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>00:20.670</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>00:18.986</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>00:11.921</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>00:02.590</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 45c744919..eb2b76e38 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -567,7 +567,7 @@ to run this tutorial with a real device.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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)
- 17.0659 17.2262 17.4522 16.3691 0.3964
+ 15.4771 15.4744 15.5467 15.4272 0.0315
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_rasp.html b/docs/how_to/deploy_models/deploy_model_on_rasp.html
index e93e12f7e..091b7d504 100644
--- a/docs/how_to/deploy_models/deploy_model_on_rasp.html
+++ b/docs/how_to/deploy_models/deploy_model_on_rasp.html
@@ -499,7 +499,7 @@ to run this tutorial with a real device.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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,
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></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 d26cf77a6..959284513 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,15 +409,36 @@ 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]
- 7%|6 | 11.5M/170M [00:00<00:01, 120MB/s]
- 14%|#3 | 23.0M/170M [00:00<00:01, 119MB/s]
- 26%|##5 | 43.4M/170M [00:00<00:00, 162MB/s]
- 39%|###9 | 66.5M/170M [00:00<00:00, 194MB/s]
- 50%|##### | 85.0M/170M [00:00<00:00, 189MB/s]
- 64%|######4 | 109M/170M [00:00<00:00, 209MB/s]
- 76%|#######5 | 129M/170M [00:00<00:00, 203MB/s]
- 88%|########8 | 150M/170M [00:00<00:00, 208MB/s]
-100%|##########| 170M/170M [00:00<00:00, 197MB/s]
+ 2%|2 | 3.95M/170M [00:00<00:04, 41.2MB/s]
+ 5%|4 | 8.38M/170M [00:00<00:03, 44.3MB/s]
+ 8%|7 | 13.3M/170M [00:00<00:03, 47.5MB/s]
+ 10%|# | 17.8M/170M [00:00<00:03, 43.3MB/s]
+ 13%|#2 | 22.0M/170M [00:00<00:03, 40.0MB/s]
+ 16%|#5 | 26.9M/170M [00:00<00:03, 43.4MB/s]
+ 19%|#8 | 31.5M/170M [00:00<00:03, 45.0MB/s]
+ 21%|##1 | 35.9M/170M [00:00<00:03, 44.8MB/s]
+ 24%|##3 | 40.2M/170M [00:00<00:03, 40.9MB/s]
+ 26%|##6 | 44.3M/170M [00:01<00:03, 41.5MB/s]
+ 30%|##9 | 50.1M/170M [00:01<00:02, 46.6MB/s]
+ 32%|###2 | 54.6M/170M [00:01<00:02, 45.1MB/s]
+ 35%|###5 | 60.0M/170M [00:01<00:02, 48.1MB/s]
+ 38%|###8 | 64.6M/170M [00:01<00:02, 46.6MB/s]
+ 41%|####1 | 70.3M/170M [00:01<00:02, 50.2MB/s]
+ 44%|####4 | 75.1M/170M [00:01<00:02, 44.1MB/s]
+ 47%|####6 | 79.5M/170M [00:01<00:02, 36.9MB/s]
+ 49%|####9 | 83.6M/170M [00:02<00:02, 38.5MB/s]
+ 52%|#####1 | 87.5M/170M [00:02<00:02, 38.8MB/s]
+ 54%|#####3 | 91.4M/170M [00:02<00:02, 39.2MB/s]
+ 56%|#####6 | 95.3M/170M [00:02<00:02, 37.2MB/s]
+ 58%|#####8 | 98.9M/170M [00:02<00:02, 35.8MB/s]
+ 60%|###### | 102M/170M [00:02<00:02, 30.7MB/s]
+ 63%|######3 | 107M/170M [00:02<00:01, 35.0MB/s]
+ 66%|######5 | 112M/170M [00:02<00:01, 38.5MB/s]
+ 68%|######8 | 116M/170M [00:02<00:01, 41.4MB/s]
+ 72%|#######1 | 122M/170M [00:03<00:01, 46.0MB/s]
+ 85%|########5 | 145M/170M [00:03<00:00, 101MB/s]
+ 99%|#########8| 168M/170M [00:03<00:00, 142MB/s]
+100%|##########| 170M/170M [00:03<00:00, 54.6MB/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').
@@ -483,7 +504,7 @@ torchvision rcnn models.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -515,7 +536,7 @@ 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 16.965 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.402 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 a8844ebe7..694ec3340 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,9 +450,9 @@ 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]
- 22%|##2 | 3.05M/13.6M [00:00<00:00, 31.3MB/s]
- 48%|####7 | 6.48M/13.6M [00:00<00:00, 33.7MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 60.5MB/s]
+ 16%|#5 | 2.14M/13.6M [00:00<00:00, 22.3MB/s]
+ 37%|###7 | 5.02M/13.6M [00:00<00:00, 26.7MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 51.9MB/s]
</pre></div>
</div>
</div>
@@ -504,7 +504,7 @@ standard Relay operators before compilation.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -546,7 +546,7 @@ 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)
- 90.6628 90.5379 94.8582 90.3709 0.6191
+ 90.4832 90.5345 90.7676 89.8992 0.2472
</pre></div>
</div>
<div class="admonition note">
@@ -585,7 +585,7 @@ 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 9.707 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.824 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 d5e3ba7fb..1a0f3829d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -510,7 +510,7 @@ target platform that you are interested in.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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)
- 122.6569 122.6277 123.4709 121.9520 0.3226
+ 119.5748 119.3936 120.9184 117.3421 0.6355
</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 54.061 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.731 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 3638b4f8a..9e54d579a 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -476,13 +476,13 @@ for calibration. But the accuracy might be impacted.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
/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,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.394 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.716 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 0a6784792..ec52a105c 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,22 +415,22 @@ 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%|5 | 7056/132723 [00:00<00:01, 70554.18KB/s]
- 12%|#1 | 15397/132723 [00:00<00:01, 78107.78KB/s]
- 18%|#7 | 23875/132723 [00:00<00:01, 81147.81KB/s]
- 24%|##4 | 32347/132723 [00:00<00:01, 82553.31KB/s]
- 31%|### | 40814/132723 [00:00<00:01, 83315.20KB/s]
- 37%|###7 | 49300/132723 [00:00<00:00, 83838.79KB/s]
- 44%|####3 | 57779/132723 [00:00<00:00, 84146.03KB/s]
- 50%|####9 | 66194/132723 [00:00<00:00, 83874.42KB/s]
- 56%|#####6 | 74713/132723 [00:00<00:00, 84279.33KB/s]
- 63%|######2 | 83247/132723 [00:01<00:00, 84603.85KB/s]
- 69%|######9 | 91772/132723 [00:01<00:00, 84796.95KB/s]
- 76%|#######5 | 100359/132723 [00:01<00:00, 85120.98KB/s]
- 82%|########2 | 109031/132723 [00:01<00:00, 85602.95KB/s]
- 89%|########8 | 117592/132723 [00:01<00:00, 85559.16KB/s]
- 95%|#########5| 126318/132723 [00:01<00:00, 86069.30KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 84143.39KB/s]
+ 5%|4 | 6624/132723 [00:00<00:01, 66233.75KB/s]
+ 12%|#1 | 15411/132723 [00:00<00:01, 78954.64KB/s]
+ 18%|#8 | 24166/132723 [00:00<00:01, 82875.38KB/s]
+ 25%|##4 | 32946/132723 [00:00<00:01, 84812.20KB/s]
+ 31%|###1 | 41720/132723 [00:00<00:01, 85867.03KB/s]
+ 38%|###8 | 50513/132723 [00:00<00:00, 86567.51KB/s]
+ 45%|####4 | 59245/132723 [00:00<00:00, 86810.42KB/s]
+ 51%|#####1 | 68091/132723 [00:00<00:00, 87333.44KB/s]
+ 58%|#####7 | 76933/132723 [00:00<00:00, 87669.40KB/s]
+ 65%|######4 | 85700/132723 [00:01<00:00, 87505.83KB/s]
+ 71%|#######1 | 94451/132723 [00:01<00:00, 87335.74KB/s]
+ 78%|#######7 | 103234/132723 [00:01<00:00, 87484.39KB/s]
+ 84%|########4 | 111983/132723 [00:01<00:00, 87308.32KB/s]
+ 91%|######### | 120734/132723 [00:01<00:00, 87367.85KB/s]
+ 98%|#########7| 129511/132723 [00:01<00:00, 87486.12KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 86136.72KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -459,7 +459,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -475,7 +475,7 @@ 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 32.795 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 19.691 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 0db4e2b11..9d144e8ba 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>11:14.091</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:14.970</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:16.965</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>02:32.795</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>01:54.061</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>01:27.394</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>01:09.707</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>00:30.382</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>00:22.577</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>00:00.211</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>03:02.402</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>02:19.691</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>01:51.731</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>01:08.716</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>01:03.824</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>00:27.462</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>00:20.964</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>00:00.180</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 317e7a959..dc2f5b3dc 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -400,7 +400,7 @@ y: [0.28239584 0.22104536 0.6862221 ]
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
z: [0.7996937 1.168008 1.4516819]
</pre></div>
@@ -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.zip15295a23-de49-4ba7-b230-e81e8057d888 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.zip23265740-86f7-4464-8b57-beefc963940c 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>
@@ -652,7 +652,7 @@ 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>Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registerd for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 57fcbda90..9ae23e94c 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>00:39.910</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.455</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:36.186</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>00:02.377</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>00:01.130</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>00:00.218</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>00:34.075</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>00:02.182</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>00:01.008</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>00:00.190</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_infra.html b/docs/how_to/extend_tvm/use_pass_infra.html
index ba2e6ca87..e43a5b1a8 100644
--- a/docs/how_to/extend_tvm/use_pass_infra.html
+++ b/docs/how_to/extend_tvm/use_pass_infra.html
@@ -406,7 +406,7 @@ examples for each of them.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%0 = nn.conv2d(%x, %weight, padding=[0, 0, 0, 0]) /* ty=Tensor[(1, 64, 54, 54), float32] */;
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 0e7354131..59bef0b01 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: 6494us [6494us] (45.82%; 45.82%)
-FoldScaleAxis: 7677us [3us] (54.18%; 54.18%)
- FoldConstant: 7674us [1580us] (54.15%; 99.96%)
- InferType: 6094us [6094us] (43.00%; 79.41%)
+InferType: 5969us [5969us] (45.49%; 45.49%)
+FoldScaleAxis: 7153us [3us] (54.51%; 54.51%)
+ FoldConstant: 7150us [1461us] (54.49%; 99.96%)
+ InferType: 5689us [5689us] (43.35%; 79.56%)
</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: 6260us [6260us] (44.96%; 44.96%)
-FoldScaleAxis: 7665us [3us] (55.04%; 55.04%)
- FoldConstant: 7662us [1578us] (55.02%; 99.96%)
- InferType: 6084us [6084us] (43.69%; 79.40%)
+InferType: 5766us [5766us] (44.65%; 44.65%)
+FoldScaleAxis: 7148us [2us] (55.35%; 55.35%)
+ FoldConstant: 7146us [1497us] (55.33%; 99.98%)
+ InferType: 5648us [5648us] (43.74%; 79.04%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
@@ -640,7 +640,7 @@ profile result.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 2c6bbb369..3bef660ba 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,11 +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>/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-Convolution: 54.164380 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 37.543247 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 a8f62159d..585b1b1f4 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,11 +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>/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-conv2d with tensor core: 6.624399 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.344750 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 23ddeaf40..d9c0b3cae 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,10 +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: 0.019481
-/workspace/python/tvm/target/target.py:317: 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. "
-Baseline: 3.300680
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018099
+Baseline: 3.421486
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -496,7 +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: 0.331405
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300247
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -565,7 +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: 0.345347
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.342873
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -628,7 +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: 0.134943
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.111848
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -713,7 +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: 0.112714
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108546
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -801,7 +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: 0.114435
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.108801
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -893,7 +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: 0.147957
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144627
</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 8b4350837..bfdf7e6a5 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>00:35.841</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.792</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:33.115</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>00:01.448</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>00:01.279</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>00:32.307</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>00:01.295</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>00:01.190</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 01cb27e5f..d26d56240 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>05:04.511</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>03:32.007</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:25.931</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>01:21.032</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>00:41.416</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>00:17.603</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>00:09.448</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>00:09.080</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>01:19.067</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>01:05.111</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>00:40.474</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>00:09.386</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>00:09.244</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>00:08.726</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 b4e95ad79..a4ec6f552 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
@@ -471,675 +471,36 @@ cooperative fetching, unrolling and operator fusion.</p>
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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 168), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 168), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 280), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 280), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 336), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 392), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 392), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 18), 81) < 72) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 2), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 560), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 616), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 616), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 24), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 672), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 728), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 728), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 784), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 840), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 840), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 896), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 896), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 952), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 952), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1064), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1120), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1120), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1176), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1176), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 17), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1232), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 8), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1288)] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
+ for (ff.outer.inner.init: int32, 0, 2) {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[ff.outer.inner.init] = 0f32
+ }
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_1, 56)) < 9), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + threadIdx.x_1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*392) + threadIdx.x_1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((ax0 [...]
+ }
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((blockIdx.x*73728) + cse_var_1) + (threadIdx.x_2 + 56))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 112), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 21), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 80), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 35), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 136), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 104), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 63), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 72), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 128), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 77), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 96), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 91), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 105), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 120), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 119), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 88), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 133), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 112), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 154), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 80), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 161), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 136), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 175), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 104), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 182), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 189), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 72), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 128), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 203), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 210), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 96), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 217), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 231), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 120), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 238), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 245), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 88), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 259), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 266), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 112), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 273), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 80), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[((((blockIdx.x*73728) + cse_var_1) + floormod((threadIdx.x_2 + 136), 144)) + 69120)]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
+ if @tir.likely((threadIdx.x_2 < 384), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 24)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + (ry.outer.outer*3)) + floormod(threadIdx.x_2, 3))]
}
- for (rc.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1152)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1153)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1154)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1155)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1156)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1157)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1158)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1159)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1160)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1161)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1162)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1163)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1164)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1165)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1166)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1167)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1168)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1169)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1170)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1171)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1172)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1173)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1174)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1175)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1176)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1177)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1178)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1179)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1180)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1181)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1182)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1183)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1184)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1185)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1186)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1187)]))
+ for (rx.outer.inner: int32, 0, 3) {
+ for (ff.outer.inner: int32, 0, 2) {
+ for (rc.inner: int32, 0, 8) {
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((((rc.inner*63) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*48) + (ff.outer.inner*24)) + (rc.inner*3)) + rx.outer.inner)]))
+ }
+ }
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner) + 392)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1177,11 +538,7 @@ 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>/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-Execution time of this operator: 0.163 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.351 ms
</pre></div>
</div>
</div>
@@ -1212,35 +569,35 @@ 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=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=8)
-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=2)
+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=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=4)
-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=3)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+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)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, 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=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=8)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+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=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)
@@ -1260,19 +617,17 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
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)
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=56)
+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=392)
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=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=56)
+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=392)
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", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
-/workspace/python/tvm/target/target.py:317: 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. "
#ifdef _WIN32
using uint = unsigned int;
@@ -1287,607 +642,36 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
- conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((9 <= ((((int)threadIdx.x) + 6) % 81)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 81) * 49)) + ((((((int)threadIdx.x) + 6) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 504) / 81) * 49)) + (((((int)threadIdx.x) / 9) + 2) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + ((((((int)threadIdx.x) + 11) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 8) {
- pad_temp_shared[(((int)threadIdx.x) + 1288)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 56)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 80))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 136) % 144))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 48))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 16))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 72))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 40))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 64))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 120) % 144))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 32))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 88))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 56))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 80))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 136) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 48))];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 16))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 72))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 40))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 64))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 120) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 32))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 88))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2072) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 56))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 80))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + (((int)threadIdx.x) + 136)) + 69120)];
- }
- __syncthreads();
- 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 * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1152)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1153)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1154)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1155)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1156)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1157)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1158)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1159)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1160)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1161)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1162)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1163)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1164)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1165)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1166)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1167)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1168)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1169)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1170)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1171)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1172)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1173)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1174)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1175)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1176)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1177)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1178)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1179)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1180)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1181)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1182)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1183)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1184)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1185)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1186)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1187)]));
+extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[504];
+ __shared__ float kernel_shared[384];
+ for (int ff_outer_inner_init = 0; ff_outer_inner_init < 2; ++ff_outer_inner_init) {
+ conv2d_nchw[ff_outer_inner_init] = 0.000000e+00f;
+ }
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) / 56)) < 9) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x))] = (((((1 <= (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer)) && ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused [...]
+ }
+ }
+ if (((int)threadIdx.x) < 384) {
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ }
+ __syncthreads();
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((((rc_inner * 63) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 48) + (ff_outer_inner * 24)) + (rc_inner * 3)) + rx_outer_inner)]));
+ }
+ }
+ }
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner) + 392)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1925,7 +709,7 @@ 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 25.931 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.111 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_arm.html b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
index d5a489c78..b3d293acf 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
@@ -575,7 +575,7 @@ The task scheduler will just optimize this objective.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get model...
Extract tasks...
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
========== Task 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 84b71f8e9..5f72e799f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -473,7 +473,7 @@ The task scheduler will just optimize this objective.</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>Extract tasks...
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
========== Task 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 64], [1, 56, 56, 64]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -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)
- 9.7968 9.7873 9.8379 9.7650 0.0305
+ 9.8867 9.8886 9.9073 9.8642 0.0176
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
index ac3c36a2d..4c537ad59 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
@@ -488,7 +488,7 @@ The task scheduler will just optimize this objective.</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>Extract tasks...
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
========== Task 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 2f54015d2..54d474f9e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -496,7 +496,7 @@ The task scheduler will just optimize this objective.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get model...
Extract tasks...
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
========== Task 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -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)
- 764.5206 764.1332 765.3251 764.1035 0.5690
+ 807.9377 808.4186 809.2553 806.1391 1.3168
</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 21.032 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.067 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 97844292d..ada459ad7 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,26 +600,78 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [128], [])[((i.inner.init*16) + j.init)] = 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])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_2: int32 = ((i.inner*16) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ 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
+ }
+ }
+ 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 + 1)
+ let cse_var_16: int32 = (cse_var_18 + 11)
+ let cse_var_15: int32 = (cse_var_18 + 12)
+ let cse_var_14: int32 = (cse_var_18 + 13)
+ let cse_var_13: int32 = (cse_var_18 + 14)
+ let cse_var_12: int32 = (cse_var_18 + 15)
+ let cse_var_11: int32 = (cse_var_18 + 2)
+ let cse_var_10: int32 = (cse_var_18 + 3)
+ let cse_var_9: int32 = (cse_var_18 + 4)
+ let cse_var_8: int32 = (cse_var_18 + 5)
+ let cse_var_7: int32 = (cse_var_18 + 6)
+ let cse_var_6: int32 = (cse_var_18 + 7)
+ let cse_var_5: int32 = (cse_var_18 + 8)
+ let cse_var_4: int32 = (cse_var_18 + 9)
+ let cse_var_3: int32 = (cse_var_18 + 10)
+ {
+ 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_17] = (compute_5[cse_var_17] + (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_11] = (compute_5[cse_var_11] + (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_10] = (compute_5[cse_var_10] + (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_9] = (compute_5[cse_var_9] + (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_8] = (compute_5[cse_var_8] + (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_7] = (compute_5[cse_var_7] + (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_6] = (compute_5[cse_var_6] + (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_5] = (compute_5[cse_var_5] + (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_4] = (compute_5[cse_var_4] + (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_3] = (compute_5[cse_var_3] + (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_16] = (compute_5[cse_var_16] + (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_15] = (compute_5[cse_var_15] + (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_14] = (compute_5[cse_var_14] + (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_13] = (compute_5[cse_var_13] + (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_12] = (compute_5[cse_var_12] + (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 (i0.inner: int32, 0, 8) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ 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))
}
}
}
@@ -658,9 +710,7 @@ 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>/workspace/python/tvm/target/target.py:317: 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. "
-Execution time of this operator: 1.528 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.850 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 6d230debf..e0b4c9d4c 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>00:45.182</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.748</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.238</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>00:00.246</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>00:00.234</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>00:00.233</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>00:00.231</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>00:45.949</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>00:00.209</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>00:00.198</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>00:00.196</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>00:00.196</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 f5f3e2804..656ebfefa 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -532,9 +532,9 @@ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -655,9 +655,9 @@ No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -778,9 +778,9 @@ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -901,9 +901,9 @@ No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1024,9 +1024,9 @@ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1142,15 +1142,15 @@ 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: 43.22/43.22 result: MeasureResult(costs=(0.005356313578947369,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6191003322601318, timestamp=1653698537.7085912) [('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: 0.00/43.22 result: Traceback (most recent call last):
+No: 6 GFLOPS: 92.36/92.36 result: MeasureResult(costs=(0.002506575395833333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0522191524505615, timestamp=1653700071.3242364) [('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: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1266,14 +1266,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1389,14 +1389,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -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: 0.00/43.22 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/92.36 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
@@ -1530,14 +1530,14 @@ No: 10 GFLOPS: 0.00/43.22 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1653,14 +1653,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1776,14 +1776,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -1899,14 +1899,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -2022,14 +2022,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -2145,14 +2145,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -2268,14 +2268,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -2391,14 +2391,14 @@ 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: 0.00/43.22 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/92.36 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 223, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 225, in build
input_mod = lower(inputs, args, name=name, binds=binds)
- File "/workspace/python/tvm/driver/build_module.py", line 131, in lower
+ File "/workspace/python/tvm/driver/build_module.py", line 133, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
@@ -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: 0.00/43.22 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/92.36 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: 0x00007fbeb4255fa2
+ 12: 0x00007f6b81a8dfa2
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: 144.61/144.61 result: MeasureResult(costs=(0.0016009116000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4389643669128418, timestamp=1653698564.3018105) [('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: 143.87/143.87 result: MeasureResult(costs=(0.00160905357,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.412313461303711, timestamp=1653700090.8098168) [('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,
@@ -2706,11 +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
-/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-Time cost of this operator: 0.001958
+Time cost of this operator: 0.002006
</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/tune_with_autotvm/tune_relay_cuda.html b/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
index d806ebb7c..779ce262b 100644
--- a/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_relay_cuda.html
@@ -452,7 +452,7 @@ We can also load models from MXNet, ONNX and TensorFlow.</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>/workspace/python/tvm/target/target.py:370: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/target/target.py:371: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
warnings.warn("Try specifying cuda arch by adding 'arch=sm_xx' to your target.")
</pre></div>
</div>
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index d5afd4c4e..917c1881e 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -550,15 +550,15 @@ the tuned operator.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
########## 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 310.2 98.732 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.981 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.902 0.287 (1, 1, 10, 10, 3) 1 1
-Total_time - 314.184 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.9 98.759 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.953 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 0.288 (1, 1, 10, 10, 3) 1 1
+Total_time - 314.806 - - - -
</pre></div>
</div>
</div>
@@ -610,10 +610,10 @@ 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 219.2 98.647 (1, 1, 10, 10, 6) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.176 0.979 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.831 0.374 (1, 3, 10, 10, 1) 1 1
-Total_time - 222.207 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 195.7 98.729 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.72 0.868 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.8 0.404 (1, 3, 10, 10, 1) 1 1
+Total_time - 198.22 - - - -
</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/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 57a9240a6..0e74122ca 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:49.065</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:48.233</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.479</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>00:03.950</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>00:00.213</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>00:00.212</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>00:00.212</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>00:44.180</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>00:03.494</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>00:00.193</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>00:00.184</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>00:00.181</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 1474ce8ee..e66892e40 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>00:12.028</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:05.299</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:10.059</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>00:01.739</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>00:00.230</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>00:03.495</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>00:01.603</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>00:00.201</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_relay/using_external_lib.html b/docs/how_to/work_with_relay/using_external_lib.html
index 25a1871de..31a403d18 100644
--- a/docs/how_to/work_with_relay/using_external_lib.html
+++ b/docs/how_to/work_with_relay/using_external_lib.html
@@ -402,7 +402,7 @@ By setting the logging level to DEBUG, the result of Relay graph compilation wil
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -827,7 +827,7 @@ To do that, all we need to do is to append the option ” -libs=cudnn” to the
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/work_with_schedules/extern_op.html b/docs/how_to/work_with_schedules/extern_op.html
index ccba133c4..e951acdf1 100644
--- a/docs/how_to/work_with_schedules/extern_op.html
+++ b/docs/how_to/work_with_schedules/extern_op.html
@@ -405,11 +405,6 @@ We can further mix schedulable TVM calls that add a bias term to the result.</p>
<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">d</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</sp [...]
</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>/workspace/python/tvm/target/target.py:317: 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. "
-</pre></div>
-</div>
</div>
<div class="section" id="extern-contrib-wrappers">
<h2>Extern Contrib Wrappers<a class="headerlink" href="#extern-contrib-wrappers" title="Permalink to this headline">¶</a></h2>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 0b30c7e42..791fee274 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -376,12 +376,7 @@ In the following example, we use <a class="reference internal" href="../../refer
</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>/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-
-#ifdef _WIN32
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>#ifdef _WIN32
using uint = unsigned int;
using uchar = unsigned char;
using ushort = unsigned short;
@@ -429,10 +424,7 @@ The following code use te.exp instead, which create an intrinsic call
</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>/workspace/python/tvm/target/target.py:317: 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. "
-
-#ifdef _WIN32
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>#ifdef _WIN32
using uint = unsigned int;
using uchar = unsigned char;
using ushort = unsigned short;
@@ -512,10 +504,7 @@ fast math version <code class="code docutils literal notranslate"><span class="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>/workspace/python/tvm/target/target.py:317: 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. "
-
-#ifdef _WIN32
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>#ifdef _WIN32
using uint = unsigned int;
using uchar = unsigned char;
using ushort = unsigned short;
@@ -577,10 +566,7 @@ The following example add an intrinsic <code class="code docutils literal notran
</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>/workspace/python/tvm/target/target.py:317: 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. "
-
-#ifdef _WIN32
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>#ifdef _WIN32
using uint = unsigned int;
using uchar = unsigned char;
using ushort = unsigned short;
diff --git a/docs/how_to/work_with_schedules/reduction.html b/docs/how_to/work_with_schedules/reduction.html
index b15bd6b91..fae29c93b 100644
--- a/docs/how_to/work_with_schedules/reduction.html
+++ b/docs/how_to/work_with_schedules/reduction.html
@@ -549,12 +549,7 @@ columns by threadIdx.x and finally do a cross thread reduction over threadIdx.x<
</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>/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-
-#if defined(__CUDA_ARCH__) && (__CUDA_ARCH__ < 700)
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>#if defined(__CUDA_ARCH__) && (__CUDA_ARCH__ < 700)
#define __shfl_sync(mask, var, lane, width) \
__shfl((var), (lane), (width))
diff --git a/docs/how_to/work_with_schedules/scan.html b/docs/how_to/work_with_schedules/scan.html
index b786360e1..a29d9b222 100644
--- a/docs/how_to/work_with_schedules/scan.html
+++ b/docs/how_to/work_with_schedules/scan.html
@@ -433,13 +433,6 @@ numpy to verify the correctness of the result.</p>
<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</span><span class="o">.</span><span class="n">cumsum</span><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0 [...]
</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>/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-</pre></div>
-</div>
</div>
<div class="section" id="multi-stage-scan-cell">
<h2>Multi-Stage Scan Cell<a class="headerlink" href="#multi-stage-scan-cell" title="Permalink to this headline">¶</a></h2>
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 e062fa138..c314b551b 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>00:05.885</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.095</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.142</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>00:01.159</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>00:00.754</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>00:00.743</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>00:00.337</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>00:00.257</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>00:00.254</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>00:00.239</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>00:01.924</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>00:00.776</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>00:00.702</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>00:00.662</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>00:00.305</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>00:00.254</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>00:00.236</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>00:00.235</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>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index f4ad16d2b..5cba3d888 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/tmpaeu1tnrm/input0.cc'\nsource_filename = \"/tmp/tmpaeu1tnrm/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/tmp8lr3zj54/input0.cc'\nsource_filename = \"/tmp/tmp8lr3zj54/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)
@@ -576,11 +576,6 @@ ensure our implementation is correct.</p>
<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="o">.</span><span class="n">T</span><sp [...]
</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>/workspace/python/tvm/target/target.py:317: 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. "
-</pre></div>
-</div>
</div>
<div class="section" id="reduce-update-for-tensorize">
<h2>Reduce-update for Tensorize<a class="headerlink" href="#reduce-update-for-tensorize" title="Permalink to this headline">¶</a></h2>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index e2560543c..240873c05 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1157,7 +1157,7 @@ initialization order?).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.LocalBuilder">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">LocalBuilder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><sp [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">LocalBuilder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><sp [...]
<dd><p>LocalBuilder use local CPU cores to build programs in parallel.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
@@ -1715,7 +1715,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1752,7 +1752,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index c1efccf29..85f113290 100644
--- a/docs/reference/api/typedoc/classes/bytestreamreader.html
+++ b/docs/reference/api/typedoc/classes/bytestreamreader.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 8a5045553..74254d9d4 100644
--- a/docs/reference/api/typedoc/classes/cachedcallstack.html
+++ b/docs/reference/api/typedoc/classes/cachedcallstack.html
@@ -144,7 +144,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L223">memory.ts:223</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">temp<wbr>Args<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><a href="../interfaces/disposable.html" class="tsd-signature-type">Disposable</a><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L208">memory.ts:208</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -194,7 +194,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L312">memory.ts:312</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L284">memory.ts:284</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L388">memory.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -300,7 +300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L376">memory.ts:376</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -340,7 +340,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L267">memory.ts:267</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -373,7 +373,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L243">memory.ts:243</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -390,7 +390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L321">memory.ts:321</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -422,7 +422,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L252">memory.ts:252</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -444,7 +444,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L359">memory.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -470,7 +470,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L342">memory.ts:342</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -496,7 +496,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L350">memory.ts:350</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -522,7 +522,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L326">memory.ts:326</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -548,7 +548,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L363">memory.ts:363</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -574,7 +574,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L346">memory.ts:346</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -600,7 +600,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L334">memory.ts:334</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/dldatatype.html b/docs/reference/api/typedoc/classes/dldatatype.html
index 3a64330f1..eac7a81a9 100644
--- a/docs/reference/api/typedoc/classes/dldatatype.html
+++ b/docs/reference/api/typedoc/classes/dldatatype.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index d4844054e..f823306d8 100644
--- a/docs/reference/api/typedoc/classes/dldevice.html
+++ b/docs/reference/api/typedoc/classes/dldevice.html
@@ -118,7 +118,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 138b89768..eb411273d 100644
--- a/docs/reference/api/typedoc/classes/environment.html
+++ b/docs/reference/api/typedoc/classes/environment.html
@@ -125,7 +125,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/environment.ts#L86">environment.ts:86</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<aside class="tsd-sources">
<p>Implementation of <a href="../interfaces/libraryprovider.html">LibraryProvider</a>.<a href="../interfaces/libraryprovider.html#imports">imports</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/environment.ts#L70">environment.ts:70</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/environment.ts#L69">environment.ts:69</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -210,7 +210,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">ctypes.FTVMWasmPackedCFunc</span><span class="tsd-signature-symbol"> | </span><span class="tsd-signature-type">undefined</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = [undefined,]</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/environment.ts#L78">environment.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -228,7 +228,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<wbr>Free<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/environment.ts#L84">environment.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/environment.ts#L105">environment.ts:105</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ffilibrary.html b/docs/reference/api/typedoc/classes/ffilibrary.html
index 2ca5144fd..e8623ccb5 100644
--- a/docs/reference/api/typedoc/classes/ffilibrary.html
+++ b/docs/reference/api/typedoc/classes/ffilibrary.html
@@ -131,7 +131,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index e8e025abb..c66e966d9 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index c5168ee61..37e9b7759 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 7a537d919..4153c877a 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L40">memory.ts:40</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L32">memory.ts:32</a></li>
</ul>
</aside>
</section>
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L33">memory.ts:33</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L154">memory.ts:154</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L90">memory.ts:90</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L97">memory.ts:97</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L74">memory.ts:74</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L81">memory.ts:81</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L104">memory.ts:104</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L132">memory.ts:132</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L60">memory.ts:60</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L67">memory.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index af0b82ab7..82f5c0479 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 1fde60e5d..d7eff34eb 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index ee08ae5f2..ec8aa884a 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 4b11b8a55..2ed6a197c 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 20450c5a0..88923647b 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index f6959ac72..d1c0c33af 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index d128d6148..bd6a29bef 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 7aa5357f1..cb8d2cee2 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 1fd4c967f..4a2f07403 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 8077356db..8535790a6 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index aa63d328c..e13fba03c 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 2bb1b988d..4189d7935 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 94ef37676..b68b62d57 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 9989818ef..df5c5a0d8 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 5d4062d3a..624e7aaf8 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/80d954919/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/afb67e64a/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 126b7c454..146cc21b0 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index ec1e54e51..9f3493b2d 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:22.062</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:19.852</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:21.841</strong>: <a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></li>
-<li><p><strong>00:00.221</strong>: <a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></li>
+<li><p><strong>00:19.668</strong>: <a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></li>
+<li><p><strong>00:00.183</strong>: <a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html b/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
index ecf111bbb..6ca69e0ba 100644
--- a/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
+++ b/docs/topic/vta/tutorials/autotvm/tune_relay_vta.html
@@ -730,7 +730,7 @@ the <code class="docutils literal notranslate"><span class="pre">`TARGET</span><
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Extract tasks...
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
/workspace/python/tvm/target/target.py:255: 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. "
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 443a47a7f..a76512b4e 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -535,13 +535,13 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
/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,
/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 22.99s!
+resnet18_v1 inference graph built in 21.38s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index fa9d9ebc3..d683e6b68 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -555,11 +555,11 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
/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 15.93s!
+yolov3-tiny inference graph built in 14.83s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 6be394729..7c8aabd5e 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:31.442</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:28.066</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:48.157</strong>: <a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></li>
-<li><p><strong>00:43.285</strong>: <a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></li>
+<li><p><strong>00:46.711</strong>: <a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></li>
+<li><p><strong>00:41.355</strong>: <a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/matrix_multiply.html b/docs/topic/vta/tutorials/matrix_multiply.html
index a95a1f432..61911ea2d 100644
--- a/docs/topic/vta/tutorials/matrix_multiply.html
+++ b/docs/topic/vta/tutorials/matrix_multiply.html
@@ -811,7 +811,7 @@ into a TVM function.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/topic/vta/tutorials/optimize/convolution_opt.html b/docs/topic/vta/tutorials/optimize/convolution_opt.html
index f8f2d4169..08db3734c 100644
--- a/docs/topic/vta/tutorials/optimize/convolution_opt.html
+++ b/docs/topic/vta/tutorials/optimize/convolution_opt.html
@@ -1086,7 +1086,7 @@ ensure correctness.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
Execution statistics:
inp_load_nbytes : 114688
diff --git a/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html b/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html
index 2dffe0e36..dbd56e4d6 100644
--- a/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html
+++ b/docs/topic/vta/tutorials/optimize/matrix_multiply_opt.html
@@ -872,7 +872,7 @@ ensure correctness.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
Execution statistics:
inp_load_nbytes : 4096
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index fcd9e0a4f..9371e91c9 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.685</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.510</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:03.107</strong>: <a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></li>
-<li><p><strong>00:00.578</strong>: <a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></li>
+<li><p><strong>00:02.999</strong>: <a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></li>
+<li><p><strong>00:00.510</strong>: <a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index bbc492b7e..9555b63c9 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:01.037</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.949</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:00.526</strong>: <a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></li>
-<li><p><strong>00:00.512</strong>: <a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></li>
+<li><p><strong>00:00.487</strong>: <a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></li>
+<li><p><strong>00:00.462</strong>: <a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/vta_get_started.html b/docs/topic/vta/tutorials/vta_get_started.html
index 01223b989..52190fe07 100644
--- a/docs/topic/vta/tutorials/vta_get_started.html
+++ b/docs/topic/vta/tutorials/vta_get_started.html
@@ -672,7 +672,7 @@ we want to compile to.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 5ae56f6d8..c72d0a739 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -453,7 +453,7 @@ trials, we can load the best schedule from the log file and apply it.</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>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E*E*E
</pre></div>
</div>
</div>
@@ -545,9 +545,7 @@ 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>/workspace/python/tvm/target/target.py:317: 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. "
-Execution time of this operator: 95.226 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.881 ms
</pre></div>
</div>
</div>
@@ -613,6 +611,7 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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)
+*E
</pre></div>
</div>
</div>
@@ -623,6 +622,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.051 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_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">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 0c0b3ae33..61ee4bb49 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -659,11 +659,6 @@ best config with the same argument.</p>
<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c_np</span><span class="p">,</span> <span class="n">c_tvm</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-4</span><span class="p">)</span>
</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>/workspace/python/tvm/target/target.py:317: 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. "
-</pre></div>
-</div>
</div>
</div>
<div class="section" id="final-notes-and-summary">
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index e2bc64c9c..2252057f8 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -473,7 +473,7 @@ set.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -521,7 +521,7 @@ standard deviation.</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>{'mean': 500.36660102999804, 'median': 500.2719358000036, 'std': 0.8369663214375898}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 492.5187951512635, 'median': 492.40721066016704, 'std': 1.1536713822642573}
</pre></div>
</div>
</div>
@@ -675,179 +675,102 @@ depending on the specifics of the model and the target platform.</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>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.37/ 17.37 GFLOPS | Progress: (4/20) | 6.04 s
-[Task 1/25] Current/Best: 6.14/ 17.37 GFLOPS | Progress: (8/20) | 9.01 s
-[Task 1/25] Current/Best: 11.50/ 22.63 GFLOPS | Progress: (12/20) | 11.47 s
-[Task 1/25] Current/Best: 16.59/ 22.63 GFLOPS | Progress: (16/20) | 13.16 s
-[Task 1/25] Current/Best: 11.56/ 23.80 GFLOPS | Progress: (20/20) | 14.91 s Done.
+[Task 1/25] Current/Best: 16.85/ 22.89 GFLOPS | Progress: (16/20) | 13.68 s
+[Task 1/25] Current/Best: 11.64/ 23.94 GFLOPS | Progress: (20/20) | 15.83 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.24/ 13.21 GFLOPS | Progress: (4/20) | 3.67 s
-[Task 2/25] Current/Best: 14.11/ 18.06 GFLOPS | Progress: (8/20) | 4.97 s
-[Task 2/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (12/20) | 6.31 s
-[Task 2/25] Current/Best: 12.27/ 21.10 GFLOPS | Progress: (16/20) | 7.61 s
-[Task 2/25] Current/Best: 19.51/ 21.10 GFLOPS | Progress: (20/20) | 9.23 s Done.
+[Task 2/25] Current/Best: 12.84/ 21.46 GFLOPS | Progress: (16/20) | 8.72 s
+[Task 2/25] Current/Best: 20.08/ 21.46 GFLOPS | Progress: (20/20) | 10.18 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/ 10.39 GFLOPS | Progress: (4/20) | 5.85 s
-[Task 3/25] Current/Best: 15.50/ 16.84 GFLOPS | Progress: (8/20) | 7.78 s
-[Task 3/25] Current/Best: 14.32/ 16.84 GFLOPS | Progress: (12/20) | 9.53 s
-[Task 3/25] Current/Best: 7.16/ 23.58 GFLOPS | Progress: (16/20) | 11.47 s
-[Task 3/25] Current/Best: 12.50/ 23.58 GFLOPS | Progress: (20/20) | 15.99 s Done.
+[Task 3/25] Current/Best: 7.22/ 23.78 GFLOPS | Progress: (16/20) | 10.53 s
+[Task 3/25] Current/Best: 12.67/ 23.78 GFLOPS | Progress: (20/20) | 14.92 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.40/ 19.10 GFLOPS | Progress: (4/20) | 2.37 s
-[Task 4/25] Current/Best: 6.54/ 19.10 GFLOPS | Progress: (8/20) | 6.78 s
-[Task 4/25] Current/Best: 21.49/ 21.49 GFLOPS | Progress: (12/20) | 11.33 s
-[Task 4/25] Current/Best: 17.25/ 21.49 GFLOPS | Progress: (16/20) | 13.59 s
-[Task 4/25] Current/Best: 13.00/ 21.49 GFLOPS | Progress: (20/20) | 15.62 s Done.
+[Task 4/25] Current/Best: 17.37/ 21.99 GFLOPS | Progress: (16/20) | 8.87 s
+[Task 4/25] Current/Best: 13.49/ 21.99 GFLOPS | Progress: (20/20) | 10.70 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.67/ 10.08 GFLOPS | Progress: (4/20) | 2.54 s
-[Task 5/25] Current/Best: 11.69/ 12.76 GFLOPS | Progress: (8/20) | 4.60 s
-[Task 5/25] Current/Best: 9.74/ 17.99 GFLOPS | Progress: (12/20) | 7.69 s
-[Task 5/25] Current/Best: 11.65/ 22.40 GFLOPS | Progress: (16/20) | 9.11 s
-[Task 5/25] Current/Best: 11.62/ 22.40 GFLOPS | Progress: (20/20) | 10.99 s Done.
+[Task 5/25] Current/Best: 11.77/ 23.04 GFLOPS | Progress: (16/20) | 7.81 s
+[Task 5/25] Current/Best: 12.08/ 23.04 GFLOPS | Progress: (20/20) | 9.40 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.28/ 20.61 GFLOPS | Progress: (4/20) | 3.97 s
-[Task 6/25] Current/Best: 18.84/ 20.61 GFLOPS | Progress: (8/20) | 5.72 s
-[Task 6/25] Current/Best: 13.08/ 20.61 GFLOPS | Progress: (12/20) | 7.64 s
-[Task 6/25] Current/Best: 19.74/ 20.61 GFLOPS | Progress: (16/20) | 9.89 s
-[Task 6/25] Current/Best: 3.72/ 20.61 GFLOPS | Progress: (20/20) | 12.39 s Done.
+[Task 6/25] Current/Best: 19.94/ 20.90 GFLOPS | Progress: (16/20) | 8.44 s
+[Task 6/25] Current/Best: 3.69/ 20.90 GFLOPS | Progress: (20/20) | 10.89 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 10.90/ 12.17 GFLOPS | Progress: (4/20) | 3.61 s
-[Task 7/25] Current/Best: 19.84/ 21.04 GFLOPS | Progress: (8/20) | 5.12 s
-[Task 7/25] Current/Best: 15.44/ 21.04 GFLOPS | Progress: (12/20) | 7.03 s
-[Task 7/25] Current/Best: 12.22/ 21.04 GFLOPS | Progress: (16/20) | 9.08 s
-[Task 7/25] Current/Best: 6.46/ 21.54 GFLOPS | Progress: (20/20) | 11.53 s Done.
+[Task 7/25] Current/Best: 12.30/ 21.22 GFLOPS | Progress: (16/20) | 8.08 s
+[Task 7/25] Current/Best: 6.40/ 21.73 GFLOPS | Progress: (20/20) | 10.45 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.39/ 14.49 GFLOPS | Progress: (4/20) | 2.89 s
-[Task 8/25] Current/Best: 9.82/ 14.49 GFLOPS | Progress: (8/20) | 7.72 s
-[Task 8/25] Current/Best: 12.83/ 14.49 GFLOPS | Progress: (12/20) | 14.04 s
-[Task 8/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (16/20) | 16.13 s
-[Task 8/25] Current/Best: 20.10/ 20.10 GFLOPS | Progress: (20/20) | 22.80 s Done.
+[Task 8/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (16/20) | 12.32 s
+[Task 8/25] Current/Best: 19.87/ 19.87 GFLOPS | Progress: (20/20) | 18.73 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.08/ 15.77 GFLOPS | Progress: (4/20) | 11.93 s
-[Task 9/25] Current/Best: 22.79/ 22.79 GFLOPS | Progress: (8/20) | 13.68 s
-[Task 9/25] Current/Best: 8.24/ 22.79 GFLOPS | Progress: (12/20) | 16.06 s
-[Task 9/25] Current/Best: 17.82/ 22.79 GFLOPS | Progress: (16/20) | 18.69 s
-[Task 9/25] Current/Best: 8.92/ 22.79 GFLOPS | Progress: (20/20) | 26.60 s
-[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.00/ 18.00 GFLOPS | Progress: (4/20) | 2.54 s
-[Task 10/25] Current/Best: 15.43/ 18.00 GFLOPS | Progress: (8/20) | 4.12 s
-[Task 10/25] Current/Best: 12.85/ 19.09 GFLOPS | Progress: (12/20) | 5.64 s
-[Task 10/25] Current/Best: 19.16/ 20.57 GFLOPS | Progress: (16/20) | 6.75 s
-[Task 10/25] Current/Best: 8.94/ 20.57 GFLOPS | Progress: (20/20) | 8.27 s Done.
+[Task 9/25] Current/Best: 18.07/ 23.11 GFLOPS | Progress: (16/20) | 15.02 s
+[Task 9/25] Current/Best: 9.09/ 23.11 GFLOPS | Progress: (20/20) | 22.59 s
+[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 10/25] Current/Best: 19.22/ 20.63 GFLOPS | Progress: (16/20) | 6.18 s
+[Task 10/25] Current/Best: 8.98/ 20.63 GFLOPS | Progress: (20/20) | 7.64 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.12/ 18.04 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 11/25] Current/Best: 16.83/ 18.04 GFLOPS | Progress: (8/20) | 5.98 s
-[Task 11/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (12/20) | 8.00 s
-[Task 11/25] Current/Best: 13.33/ 21.08 GFLOPS | Progress: (16/20) | 10.82 s
-[Task 11/25] Current/Best: 19.39/ 21.53 GFLOPS | Progress: (20/20) | 12.87 s Done.
+[Task 11/25] Current/Best: 13.57/ 21.18 GFLOPS | Progress: (16/20) | 8.77 s
+[Task 11/25] Current/Best: 19.52/ 21.50 GFLOPS | Progress: (20/20) | 10.72 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.77/ 18.22 GFLOPS | Progress: (4/20) | 5.31 s
-[Task 12/25] Current/Best: 5.28/ 18.22 GFLOPS | Progress: (8/20) | 9.05 s
-[Task 12/25] Current/Best: 19.19/ 19.19 GFLOPS | Progress: (12/20) | 11.01 s
-[Task 12/25] Current/Best: 14.11/ 19.19 GFLOPS | Progress: (16/20) | 13.80 s
-[Task 12/25] Current/Best: 15.21/ 19.19 GFLOPS | Progress: (20/20) | 15.75 s Done.
+[Task 12/25] Current/Best: 15.33/ 19.11 GFLOPS | Progress: (16/20) | 10.11 s
+[Task 12/25] Current/Best: 15.21/ 19.11 GFLOPS | Progress: (20/20) | 11.98 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.23/ 17.29 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 13/25] Current/Best: 15.80/ 20.80 GFLOPS | Progress: (8/20) | 6.12 s
-[Task 13/25] Current/Best: 19.45/ 21.49 GFLOPS | Progress: (12/20) | 9.01 s
-[Task 13/25] Current/Best: 12.22/ 21.49 GFLOPS | Progress: (16/20) | 12.41 s
-[Task 13/25] Current/Best: 18.65/ 21.49 GFLOPS | Progress: (20/20) | 14.62 s Done.
+[Task 13/25] Current/Best: 12.31/ 21.81 GFLOPS | Progress: (16/20) | 8.90 s
+[Task 13/25] Current/Best: 18.73/ 21.81 GFLOPS | Progress: (20/20) | 11.05 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.62/ 13.62 GFLOPS | Progress: (4/20) | 3.24 s
-[Task 14/25] Current/Best: 6.11/ 13.62 GFLOPS | Progress: (8/20) | 5.46 s
-[Task 14/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (12/20) | 8.04 s
-[Task 14/25] Current/Best: 14.91/ 20.51 GFLOPS | Progress: (16/20) | 9.92 s Done.
-
-[Task 14/25] Current/Best: 17.01/ 20.51 GFLOPS | Progress: (20/20) | 11.64 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.08/ 17.56 GFLOPS | Progress: (4/20) | 2.66 s
-[Task 15/25] Current/Best: 14.39/ 17.86 GFLOPS | Progress: (8/20) | 4.19 s
-[Task 15/25] Current/Best: 10.34/ 22.06 GFLOPS | Progress: (12/20) | 6.44 s
-[Task 15/25] Current/Best: 20.24/ 22.06 GFLOPS | Progress: (16/20) | 9.51 s
-[Task 15/25] Current/Best: 9.64/ 22.06 GFLOPS | Progress: (20/20) | 10.71 s
+[Task 14/25] Current/Best: 17.03/ 19.90 GFLOPS | Progress: (16/20) | 8.06 s
+[Task 14/25] Current/Best: 17.19/ 19.90 GFLOPS | Progress: (20/20) | 9.45 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 15/25] Current/Best: 20.35/ 22.39 GFLOPS | Progress: (16/20) | 6.21 s
+[Task 15/25] Current/Best: 9.72/ 22.39 GFLOPS | Progress: (20/20) | 7.26 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.17/ 20.17 GFLOPS | Progress: (4/20) | 2.96 s
-[Task 16/25] Current/Best: 3.03/ 20.17 GFLOPS | Progress: (8/20) | 4.58 s
-[Task 16/25] Current/Best: 19.40/ 20.17 GFLOPS | Progress: (12/20) | 5.80 s
-[Task 16/25] Current/Best: 17.71/ 20.17 GFLOPS | Progress: (16/20) | 7.19 s
-[Task 16/25] Current/Best: 9.95/ 21.80 GFLOPS | Progress: (20/20) | 9.26 s Done.
+[Task 16/25] Current/Best: 18.41/ 20.61 GFLOPS | Progress: (16/20) | 6.35 s
+[Task 16/25] Current/Best: 10.00/ 22.53 GFLOPS | Progress: (20/20) | 8.30 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 14.12/ 18.71 GFLOPS | Progress: (4/20) | 4.68 s
-[Task 17/25] Current/Best: 14.19/ 22.98 GFLOPS | Progress: (8/20) | 7.59 s
-[Task 17/25] Current/Best: 18.18/ 22.98 GFLOPS | Progress: (12/20) | 9.64 s
-[Task 17/25] Current/Best: 16.43/ 22.98 GFLOPS | Progress: (16/20) | 11.79 s
-[Task 17/25] Current/Best: 10.03/ 22.98 GFLOPS | Progress: (20/20) | 13.93 s Done.
+[Task 17/25] Current/Best: 16.53/ 23.46 GFLOPS | Progress: (16/20) | 9.42 s
+[Task 17/25] Current/Best: 10.06/ 23.46 GFLOPS | Progress: (20/20) | 11.44 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.29/ 17.74 GFLOPS | Progress: (4/20) | 3.70 s
-[Task 18/25] Current/Best: 10.54/ 17.74 GFLOPS | Progress: (8/20) | 7.25 s
-[Task 18/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 9.19 s
-[Task 18/25] Current/Best: 9.85/ 18.91 GFLOPS | Progress: (16/20) | 12.81 s
-[Task 18/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (20/20) | 14.34 s Done.
+[Task 18/25] Current/Best: 10.06/ 19.45 GFLOPS | Progress: (16/20) | 9.32 s
+[Task 18/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (20/20) | 10.76 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 6.04/ 20.21 GFLOPS | Progress: (4/20) | 6.21 s
-[Task 19/25] Current/Best: 2.61/ 20.21 GFLOPS | Progress: (8/20) | 9.48 s
-[Task 19/25] Current/Best: 17.89/ 20.65 GFLOPS | Progress: (12/20) | 12.33 s
-[Task 19/25] Current/Best: 13.97/ 21.58 GFLOPS | Progress: (16/20) | 15.17 s
-[Task 19/25] Current/Best: 2.70/ 22.94 GFLOPS | Progress: (20/20) | 17.94 s Done.
+[Task 19/25] Current/Best: 14.42/ 22.06 GFLOPS | Progress: (16/20) | 11.55 s
+[Task 19/25] Current/Best: 2.71/ 23.90 GFLOPS | Progress: (20/20) | 14.21 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.30/ 15.04 GFLOPS | Progress: (4/20) | 3.29 s Done.
- Done.
-
-[Task 20/25] Current/Best: 10.10/ 15.04 GFLOPS | Progress: (8/20) | 6.78 s
-[Task 20/25] Current/Best: 2.32/ 16.54 GFLOPS | Progress: (12/20) | 10.78 s
-[Task 20/25] Current/Best: 12.39/ 16.54 GFLOPS | Progress: (16/20) | 14.61 s
-[Task 20/25] Current/Best: 13.31/ 21.59 GFLOPS | Progress: (20/20) | 16.72 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.38/ 17.54 GFLOPS | Progress: (4/20) | 3.21 s
-[Task 21/25] Current/Best: 14.40/ 17.54 GFLOPS | Progress: (8/20) | 4.82 s
-[Task 21/25] Current/Best: 1.61/ 17.54 GFLOPS | Progress: (12/20) | 6.95 s
-[Task 21/25] Current/Best: 17.03/ 17.54 GFLOPS | Progress: (16/20) | 10.42 s
-[Task 21/25] Current/Best: 4.46/ 17.54 GFLOPS | Progress: (20/20) | 17.81 s
+[Task 20/25] Current/Best: 12.26/ 16.65 GFLOPS | Progress: (16/20) | 10.69 s
+[Task 20/25] Current/Best: 12.55/ 22.39 GFLOPS | Progress: (20/20) | 12.68 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 21/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 7.46 s
+[Task 21/25] Current/Best: 4.47/ 18.28 GFLOPS | Progress: (20/20) | 14.43 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.96 GFLOPS | Progress: (4/20) | 2.66 s
-[Task 22/25] Current/Best: 9.11/ 21.34 GFLOPS | Progress: (8/20) | 4.57 s
-[Task 22/25] Current/Best: 19.65/ 21.34 GFLOPS | Progress: (12/20) | 6.89 s
-[Task 22/25] Current/Best: 15.21/ 21.34 GFLOPS | Progress: (16/20) | 8.95 s
-[Task 22/25] Current/Best: 14.73/ 21.34 GFLOPS | Progress: (20/20) | 10.71 s Done.
+[Task 22/25] Current/Best: 15.67/ 22.10 GFLOPS | Progress: (16/20) | 7.14 s
+[Task 22/25] Current/Best: 14.56/ 22.10 GFLOPS | Progress: (20/20) | 8.74 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.32/ 19.89 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 23/25] Current/Best: 15.81/ 19.89 GFLOPS | Progress: (8/20) | 6.66 s
-[Task 23/25] Current/Best: 20.71/ 21.14 GFLOPS | Progress: (12/20) | 8.52 s
-[Task 23/25] Current/Best: 5.57/ 21.14 GFLOPS | Progress: (16/20) | 15.68 s
-[Task 23/25] Current/Best: 7.25/ 21.14 GFLOPS | Progress: (20/20) | 19.97 s Done.
+[Task 23/25] Current/Best: 6.44/ 21.95 GFLOPS | Progress: (16/20) | 13.34 s
+[Task 23/25] Current/Best: 7.80/ 21.95 GFLOPS | Progress: (20/20) | 17.42 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.60/ 8.60 GFLOPS | Progress: (4/20) | 11.78 s
-[Task 24/25] Current/Best: 1.89/ 8.60 GFLOPS | Progress: (8/20) | 22.77 s
-[Task 24/25] Current/Best: 3.78/ 8.60 GFLOPS | Progress: (12/20) | 34.28 s Done.
- Done.
-
-[Task 24/25] Current/Best: 7.33/ 8.60 GFLOPS | Progress: (16/20) | 39.88 s
-[Task 24/25] Current/Best: 3.18/ 8.91 GFLOPS | Progress: (20/20) | 45.90 s Done.
+[Task 24/25] Current/Best: 6.83/ 8.81 GFLOPS | Progress: (16/20) | 13.82 s
+[Task 24/25] Current/Best: 3.32/ 8.81 GFLOPS | Progress: (20/20) | 19.55 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.54/ 2.80 GFLOPS | Progress: (4/20) | 11.59 s
-[Task 25/25] Current/Best: 5.21/ 7.49 GFLOPS | Progress: (8/20) | 22.86 s
-[Task 25/25] Current/Best: 5.80/ 7.49 GFLOPS | Progress: (12/20) | 34.15 s
-[Task 25/25] Current/Best: 5.53/ 8.65 GFLOPS | Progress: (16/20) | 35.92 s
-[Task 25/25] Current/Best: 2.88/ 8.65 GFLOPS | Progress: (20/20) | 46.63 s
+[Task 25/25] Current/Best: 5.76/ 8.35 GFLOPS | Progress: (16/20) | 13.53 s
+[Task 25/25] Current/Best: 2.85/ 9.15 GFLOPS | Progress: (20/20) | 24.19 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -948,8 +871,8 @@ improvement in comparing the optimized model to the unoptimized model.</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>optimized: {'mean': 416.879001669995, 'median': 413.8142585999958, 'std': 9.18739572704193}
-unoptimized: {'mean': 500.36660102999804, 'median': 500.2719358000036, 'std': 0.8369663214375898}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 408.95329352933913, 'median': 408.035372197628, 'std': 3.4917680862039147}
+unoptimized: {'mean': 492.5187951512635, 'median': 492.40721066016704, 'std': 1.1536713822642573}
</pre></div>
</div>
</div>
@@ -963,7 +886,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 23.069 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 8 minutes 30.128 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_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">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 277ee9c37..bb786250b 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -421,11 +421,6 @@ on our webpage building server. See the detailed note in the following block.</p
<span class="n">func</span><span class="o">.</span><span class="n">export_library</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
</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>/workspace/python/tvm/target/target.py:317: 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. "
-</pre></div>
-</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>To run this tutorial with a real remote device, change <code class="code docutils literal notranslate"><span class="pre">local_demo</span></code>
@@ -501,7 +496,7 @@ device and returns the measured cost. Network overhead is excluded.</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>1.239e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.304e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index d59a32291..66c1cd4fd 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -429,7 +429,7 @@ we can schedule the following series of operations ending with <code class="code
</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>/workspace/python/tvm/target/target.py:370: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/target/target.py:371: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
warnings.warn("Try specifying cuda arch by adding 'arch=sm_xx' to your target.")
@main = primfn(a_1: handle, b_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
@@ -461,7 +461,7 @@ we can schedule the following series of operations ending with <code class="code
</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>[stage(a, placeholder(a, 0x21e1d7f0)), stage(b, placeholder(b, 0x11af1890)), 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=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xcd2e220)), stage(b, placeholder(b, 0x20545d50)), 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=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
@@ -477,13 +477,6 @@ we can schedule the following series of operations ending with <code class="code
<span class="n">tvm</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">g_nd</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">g_np</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">)</span>
</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>/workspace/python/tvm/target/target.py:317: 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. "
-/workspace/python/tvm/target/target.py:317: 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. "
-</pre></div>
-</div>
<p>TOPI also provides common neural nets operations such as _softmax_ with optimized schedule</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">tarray</span> <span class="o">=</span> <a href="../reference/api/python/te.html#tvm.te.placeholder" title="View documentation for tvm.te.placeholder"><span class="n">te</span><span class="o">.</span><span class="n">placeholder</span></a><span class="p">((</span><span class="mi">512</span><span class="p">,</span> <span class="mi">512</span><span class="p">),</span> <span class="n">name</spa [...]
<span class="n">softmax_topi</span> <span class="o">=</span> <a href="../reference/api/python/topi.html#tvm.topi.nn.softmax" title="View documentation for tvm.topi.nn.softmax"><span class="n">topi</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">softmax</span></a><span class="p">(</span><span class="n">tarray</span><span class="p">)</span>
diff --git a/docs/tutorial/relay_quick_start.html b/docs/tutorial/relay_quick_start.html
index 5a2bc7be4..59bfb74f2 100644
--- a/docs/tutorial/relay_quick_start.html
+++ b/docs/tutorial/relay_quick_start.html
@@ -501,9 +501,9 @@ in this example. Then the machine code will be generated as the module library.<
</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>/workspace/python/tvm/target/target.py:370: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/target/target.py:371: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
warnings.warn("Try specifying cuda arch by adding 'arch=sm_xx' to your target.")
-/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></div>
</div>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index e6b529497..8988739ce 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -300,20 +300,20 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:01.385</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>11:53.332</strong> total execution time for <strong>tutorial</strong> files:</p>
<ul class="simple">
-<li><p><strong>10:23.069</strong>: <a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></li>
-<li><p><strong>01:00.389</strong>: <a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></li>
-<li><p><strong>00:44.067</strong>: <a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></li>
-<li><p><strong>00:27.309</strong>: <a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></li>
-<li><p><strong>00:24.783</strong>: <a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.737</strong>: <a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></li>
-<li><p><strong>00:00.590</strong>: <a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></li>
-<li><p><strong>00:00.221</strong>: <a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></li>
-<li><p><strong>00:00.056</strong>: <a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></li>
-<li><p><strong>00:00.055</strong>: <a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></li>
-<li><p><strong>00:00.054</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
-<li><p><strong>00:00.054</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
+<li><p><strong>08:30.128</strong>: <a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></li>
+<li><p><strong>01:29.051</strong>: <a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></li>
+<li><p><strong>01:01.665</strong>: <a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></li>
+<li><p><strong>00:26.233</strong>: <a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></li>
+<li><p><strong>00:24.638</strong>: <a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></li>
+<li><p><strong>00:00.693</strong>: <a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></li>
+<li><p><strong>00:00.561</strong>: <a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></li>
+<li><p><strong>00:00.210</strong>: <a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></li>
+<li><p><strong>00:00.042</strong>: <a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></li>
+<li><p><strong>00:00.040</strong>: <a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></li>
+<li><p><strong>00:00.037</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
+<li><p><strong>00:00.034</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index a1457abf4..70b035a87 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -454,7 +454,7 @@ the inputs and outputs) as well as target language we want to compile to.</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>/workspace/python/tvm/target/target.py:317: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -513,7 +513,7 @@ helper function to run a profile of the TVM generated code.</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>Numpy running time: 0.000008
-naive: 0.000007
+naive: 0.000006
</pre></div>
</div>
</div>
@@ -604,7 +604,7 @@ factor to be the number of threads on your CPU.</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>vector: 0.000027
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000026
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -638,10 +638,10 @@ factor to be the number of threads on your CPU.</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>Operator Timing Performance
- numpy 8.202120002351875e-06 1.0
- naive 6.845e-06 0.834540338112252
-parallel 6.3488e-06 0.7740437835802872
- vector 2.7318700000000003e-05 3.3306876749141248
... 138 lines suppressed ...