You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/06/28 17:31:08 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@b733aa3ec87a1c5a6e49350bd805e187db1aca70)
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 1250f9f5e deploying docs (apache/tvm@b733aa3ec87a1c5a6e49350bd805e187db1aca70)
1250f9f5e is described below
commit 1250f9f5efec70f15cc770b6c0fa85c9a78b7a4f
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Jun 28 17:31:02 2022 +0000
deploying docs (apache/tvm@b733aa3ec87a1c5a6e49350bd805e187db1aca70)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1153 +++++++++++++-------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 86 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 6 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 2 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 138 +--
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 14 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 28 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 27 +-
docs/how_to/deploy_models/deploy_prequantized.html | 14 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1153 +++++++++++++-------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 86 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 6 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 2 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 ++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
121 files changed, 2461 insertions(+), 1773 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index c1695ebff..f57b83b5f 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -114,7 +114,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1171e2a2-a280-4ef1-89df-addf44b82fb6 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip69e2df53-adb4-4e31-9e0d-59d4885dd89b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index 67f87319a..a10f4384e 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -112,7 +112,7 @@ 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<09:08, 79.3kB/s]
0%| | 48.0k/41.5M [00:00<05:22, 135kB/s]
0%| | 96.0k/41.5M [00:00<03:44, 193kB/s]
0%| | 160k/41.5M [00:00<02:55, 247kB/s]
1%| | 320k/41.5M [00:00<01:37, 444kB/s]
1%|1 | 488k/41.5M [00:01<01:12, 590kB/s]
2%|1 | 664k/41.5M [00:01<00:59, 721kB/s]
2%|1 | 848k/41.5M [00:01<00:53, 796kB/s]
2%|2 | 1.02M/41.5M [00:01<00:50, 845kB/s]
3%|2 | 1.21M/41.5M [00:01<00:47, 893kB/s]
3%|3 | 1.41M/41.5M [00:02<00:43, 963kB/s]
4%|3 | 1.62M/41.5M [00:02<00:40, 1.02MB/s]
4%|4 | 1.83M/41.5M [00:02<00:40, 1.04MB/s]
5%|4 | 2.05M/41.5M [00:02<00:39, 1.06MB/s]
6%|5 | 2.29M/41.5M [00:02<00:36, 1.13MB/s]
6%|6 | 2.54M/41.5M [00:03<00:33, 1.21MB/s]
7%|6 | 2.80M/41.5M [00:03<00:32, 1.
25MB/s]
7%|7 | 3.08M/41.5M [00:03<00:31, 1.29MB/s]
8%|8 | 3.36M/41.5M [00:03<00:29, 1.34MB/s]
9%|8 | 3.66M/41.5M [00:03<00:27, 1.46MB/s]
10%|9 | 3.98M/41.5M [00:04<00:25, 1.52MB/s]
10%|# | 4.31M/41.5M [00:04<00:25, 1.54MB/s]
11%|#1 | 4.60M/41.5M [00:04<00:25, 1.51MB/s]
12%|#1 | 4.95M/41.5M [00:04<00:23, 1.66MB/s]
13%|#2 | 5.34M/41.5M [00:04<00:21, 1.80MB/s]
14%|#3 | 5.73M/41.5M [00:05<00:20, 1.87MB/s]
15%|#4 | 6.14M/41.5M [00:05<00:19, 1.93MB/s]
16%|#5 | 6.58M/41.5M [00:05<00:17, 2.07MB/s]
17%|#6 | 7.04M/41.5M [00:05<00:16, 2.25MB/s]
18%|#8 | 7.52M/41.5M [00:05<00:15, 2.32MB/s]
19%|#9 | 8.02M/41.5M [00:06<00:14, 2.37MB/s]
21%|## | 8.55M/41.5M [00:06<00:13, 2.50MB/s]
22%|##1 | 9.10M/41.5M [00:06<00:12, 2.73MB/s]
23%|##3 | 9.65M/41.5M [00:06<00:11, 2.82MB/s]
25%|##4 |
10.2M/41.5M [00:06<00:11, 2.84MB/s]
26%|##5 | 10.8M/41.5M [00:07<00:11, 2.83MB/s]
27%|##7 | 11.3M/41.5M [00:07<00:10, 2.95MB/s]
29%|##8 | 11.9M/41.5M [00:07<00:10, 3.05MB/s]
30%|##9 | 12.4M/41.5M [00:07<00:10, 3.02MB/s]
31%|###1 | 13.0M/41.5M [00:07<00:10, 2.95MB/s]
33%|###2 | 13.5M/41.5M [00:07<00:08, 3.27MB/s]
34%|###3 | 14.0M/41.5M [00:08<00:08, 3.51MB/s]
35%|###4 | 14.3M/41.5M [00:08<00:08, 3.36MB/s]
35%|###5 | 14.7M/41.5M [00:08<00:09, 2.86MB/s]
37%|###6 | 15.2M/41.5M [00:08<00:09, 2.83MB/s]
38%|###7 | 15.8M/41.5M [00:08<00:08, 3.28MB/s]
39%|###9 | 16.2M/41.5M [00:08<00:07, 3.49MB/s]
40%|###9 | 16.6M/41.5M [00:09<00:08, 3.10MB/s]
41%|#### | 16.9M/41.5M [00:09<00:09, 2.76MB/s]
42%|####2 | 17.5M/41.5M [00:09<00:08, 2.87MB/s]
43%|####3 | 18.0M/41.5M [00:09<00:07, 3.37MB/s]
44%|####4 | 18.5M/41.5M [00:09<00:07, 3
.44MB/s]
45%|####5 | 18.8M/41.5M [00:09<00:07, 3.04MB/s]
46%|####6 | 19.2M/41.5M [00:09<00:08, 2.81MB/s]
48%|####7 | 19.7M/41.5M [00:10<00:06, 3.47MB/s]
49%|####8 | 20.2M/41.5M [00:10<00:05, 3.72MB/s]
50%|####9 | 20.6M/41.5M [00:10<00:06, 3.18MB/s]
50%|##### | 20.9M/41.5M [00:10<00:08, 2.62MB/s]
52%|#####1 | 21.5M/41.5M [00:10<00:07, 2.86MB/s]
53%|#####3 | 22.1M/41.5M [00:10<00:06, 3.10MB/s]
55%|#####4 | 22.7M/41.5M [00:11<00:06, 3.16MB/s]
56%|#####6 | 23.3M/41.5M [00:11<00:06, 3.15MB/s]
58%|#####7 | 23.9M/41.5M [00:11<00:05, 3.17MB/s]
59%|#####9 | 24.6M/41.5M [00:11<00:05, 3.34MB/s]
61%|###### | 25.2M/41.5M [00:11<00:04, 3.47MB/s]
62%|######2 | 25.8M/41.5M [00:12<00:04, 3.46MB/s]
64%|######3 | 26.5M/41.5M [00:12<00:04, 3.42MB/s]
65%|######5 | 27.2M/41.5M [00:12<00:04, 3.47MB/s]
67%|######7 | 27.8M/41.5M [00:12<00:03, 3.80MB/s]
69%|######8
| 28.5M/41.5M [00:12<00:03, 3.85MB/s]
70%|####### | 29.2M/41.5M [00:12<00:02, 4.45MB/s]
71%|#######1 | 29.7M/41.5M [00:13<00:02, 4.22MB/s]
73%|#######2 | 30.1M/41.5M [00:13<00:03, 3.47MB/s]
74%|#######3 | 30.7M/41.5M [00:13<00:03, 3.44MB/s]
76%|#######5 | 31.4M/41.5M [00:13<00:02, 3.75MB/s]
78%|#######7 | 32.2M/41.5M [00:13<00:02, 3.86MB/s]
79%|#######9 | 32.9M/41.5M [00:13<00:02, 4.47MB/s]
81%|######## | 33.5M/41.5M [00:14<00:01, 4.61MB/s]
82%|########1 | 34.0M/41.5M [00:14<00:01, 4.11MB/s]
83%|########3 | 34.5M/41.5M [00:14<00:01, 4.48MB/s]
85%|########4 | 35.2M/41.5M [00:14<00:01, 4.93MB/s]
86%|########5 | 35.7M/41.5M [00:14<00:01, 4.35MB/s]
87%|########7 | 36.2M/41.5M [00:14<00:01, 4.49MB/s]
89%|########8 | 36.9M/41.5M [00:14<00:00, 4.86MB/s]
90%|######### | 37.4M/41.5M [00:14<00:01, 4.14MB/s]
92%|#########1| 38.0M/41.5M [00:15<00:00, 4.57MB/s]
93%|#########3| 38.7M/41.5M [00:15<00:00,
5.28MB/s]
95%|#########4| 39.2M/41.5M [00:15<00:00, 4.77MB/s]
96%|#########5| 39.8M/41.5M [00:15<00:00, 4.95MB/s]
98%|#########7| 40.6M/41.5M [00:15<00:00, 5.52MB/s]
99%|#########9| 41.1M/41.5M [00:15<00:00, 4.65MB/s]
100%|##########| 41.5M/41.5M [00:15<00:00, 2.77MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<10:06, 71.7kB/s]
0%| | 48.0k/41.5M [00:00<06:22, 114kB/s]
0%| | 96.0k/41.5M [00:00<04:29, 161kB/s]
0%| | 168k/41.5M [00:00<03:09, 229kB/s]
1%| | 224k/41.5M [00:01<02:53, 250kB/s]
1%|1 | 456k/41.5M [00:01<01:15, 568kB/s]
2%|2 | 904k/41.5M [00:01<00:37, 1.12MB/s]
4%|4 | 1.76M/41.5M [00:01<00:19, 2.17MB/s]
7%|6 | 2.75M/41.5M [00:01<00:13, 2.98MB/s]
9%|9 | 3.79M/41.5M [00:02<00:11, 3.58MB/s]
12%|#1 | 4.88M/41.5M [00:02<00:09, 4.05MB/s]
14%|#4 | 6.01M/41.5M [00:02<00:08, 4.45MB/s]
17%|#7 | 7.20M/41.5M [00:02<00:07, 4.79MB/s]
20%|## | 8.46M/41.5M [00:03<00:06, 5.14MB/s]
24%|##3 | 9.77M/41.5M [00:03<00:06, 5.46MB/s]
27%|##6 | 11.2M/41.5M [00:03<00:05, 5.79MB/s]
30%|### | 12.6M/41.5M [00:03<00:
04, 6.94MB/s]
33%|###3 | 13.8M/41.5M [00:03<00:03, 7.98MB/s]
35%|###5 | 14.7M/41.5M [00:03<00:04, 6.62MB/s]
37%|###7 | 15.5M/41.5M [00:04<00:04, 6.76MB/s]
41%|#### | 16.9M/41.5M [00:04<00:03, 8.32MB/s]
43%|####2 | 17.8M/41.5M [00:04<00:03, 6.80MB/s]
45%|####4 | 18.6M/41.5M [00:04<00:04, 5.72MB/s]
48%|####8 | 20.0M/41.5M [00:04<00:03, 6.98MB/s]
51%|##### | 21.1M/41.5M [00:04<00:02, 7.91MB/s]
53%|#####2 | 21.9M/41.5M [00:05<00:03, 6.41MB/s]
55%|#####5 | 22.9M/41.5M [00:05<00:02, 6.79MB/s]
57%|#####7 | 23.7M/41.5M [00:05<00:03, 4.72MB/s]
59%|#####9 | 24.6M/41.5M [00:05<00:03, 4.59MB/s]
62%|######1 | 25.6M/41.5M [00:05<00:03, 4.71MB/s]
64%|######4 | 26.7M/41.5M [00:06<00:03, 4.81MB/s]
67%|######7 | 27.8M/41.5M [00:06<00:02, 4.94MB/s]
70%|######9 | 29.0M/41.5M [00:06<00:02, 5.09MB/s]
73%|#######2 | 30.1M/41.5M [00:06<00:01, 6.10MB/s]
74%|#####
##4 | 30.8M/41.5M [00:06<00:01, 6.06MB/s]
76%|#######5 | 31.4M/41.5M [00:07<00:02, 4.91MB/s]
78%|#######8 | 32.6M/41.5M [00:07<00:01, 6.01MB/s]
80%|######## | 33.2M/41.5M [00:07<00:01, 6.01MB/s]
82%|########1 | 33.8M/41.5M [00:07<00:01, 4.85MB/s]
85%|########4 | 35.1M/41.5M [00:07<00:01, 5.13MB/s]
88%|########7 | 36.4M/41.5M [00:07<00:00, 6.39MB/s]
89%|########9 | 37.1M/41.5M [00:07<00:00, 6.48MB/s]
91%|######### | 37.7M/41.5M [00:08<00:00, 5.26MB/s]
94%|#########4| 39.0M/41.5M [00:08<00:00, 5.56MB/s]
97%|#########7| 40.4M/41.5M [00:08<00:00, 5.83MB/s]
100%|##########| 41.5M/41.5M [00:08<00:00, 5.03MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 0ee9b73f5..7000549a9 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -235,7 +235,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.642 seconds)
+ **Total running time of the script:** ( 1 minutes 10.545 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 179526770..7c005c3fa 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -93,7 +93,7 @@ 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]
3%|2 | 1.18M/44.7M [00:00<00:03, 12.3MB/s]
8%|7 | 3.42M/44.7M [00:00<00:02, 18.9MB/s]
18%|#7 | 7.91M/44.7M [00:00<00:01, 31.6MB/s]
38%|###8 | 17.0M/44.7M [00:00<00:00, 56.8MB/s]
79%|#######9 | 35.3M/44.7M [00:00<00:00, 105MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 86.1MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
2%|1 | 824k/44.7M [00:00<00:05, 8.29MB/s]
5%|4 | 2.18M/44.7M [00:00<00:03, 11.8MB/s]
10%|9 | 4.43M/44.7M [00:00<00:02, 17.1MB/s]
18%|#7 | 8.03M/44.7M [00:00<00:01, 25.2MB/s]
31%|###1 | 13.9M/44.7M [00:00<00:00, 38.4MB/s]
44%|####4 | 19.8M/44.7M [00:00<00:00, 46.0MB/s]
68%|######8 | 30.6M/44.7M [00:00<00:00, 68.0MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 58.9MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index 9584feb53..d840bc2ef 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -422,7 +422,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.631 seconds)
+ **Total running time of the script:** ( 1 minutes 7.088 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 670d74413..6da96d2f9 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
@@ -5,26 +5,26 @@
Computation times
=================
-**06:01.884** total execution time for **how_to_compile_models** files:
+**05:43.530** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:07.642 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:10.545 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.631 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:07.088 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:59.181 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:59.807 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:41.708 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.407 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:33.967 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.723 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.130 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.567 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.977 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.930 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:23.170 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.462 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.814 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.459 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.663 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.542 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
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 84901c569..a353e0777 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
@@ -440,7 +440,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3086 16.2930 16.7488 16.1469 0.1674
+ 16.5379 16.5268 16.6690 16.4321 0.0711
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 435df2de5..c85bb19ef 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
@@ -122,7 +122,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 2.94M/170M [00:00<00:05, 30.5MB/s]
5%|5 | 8.88M/170M [00:00<00:03, 49.0MB/s]
12%|#1 | 19.5M/170M [00:00<00:02, 77.6MB/s]
22%|##1 | 36.9M/170M [00:00<00:01, 119MB/s]
33%|###2 | 55.2M/170M [00:00<00:00, 145MB/s]
43%|####3 | 73.4M/170M [00:00<00:00, 160MB/s]
54%|#####3 | 91.7M/170M [00:00<00:00, 171MB/s]
65%|######4 | 110M/170M [00:00<00:00, 177MB/s]
76%|#######5 | 128M/170M [00:00<00:00, 182MB/s]
86%|########6 | 146M/170M [00:01<00:00, 184MB/s]
97%|#########6| 165M/170M [00:01<00:00, 186MB/s]
100%|##########| 170M/170M [00:01<00:00, 156MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|5 | 8.74M/170M [00:00<00:01, 91.5MB/s]
15%|#4 | 25.0M/170M [00:00<00:01, 138MB/s]
24%|##4 | 41.0M/170M [00:00<00:00, 152MB/s]
34%|###3 | 57.3M/170M [00:00<00:00, 159MB/s]
43%|####3 | 73.3M/170M [00:00<00:00, 162MB/s]
52%|#####2 | 88.8M/170M [00:00<00:00, 155MB/s]
61%|######1 | 104M/170M [00:00<00:00, 145MB/s]
69%|######9 | 118M/170M [00:00<00:00, 139MB/s]
77%|#######7 | 131M/170M [00:00<00:00, 136MB/s]
85%|########4 | 144M/170M [00:01<00:00, 135MB/s]
92%|#########2| 157M/170M [00:01<00:00, 134MB/s]
100%|##########| 170M/170M [00:01<00:00, 135MB/s]
100%|##########| 170M/170M [00:01<00:00, 141MB/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').
@@ -291,7 +291,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 0.945 seconds)
+ **Total running time of the script:** ( 3 minutes 13.460 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 bde0b8ec8..bc0d1f880 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -219,7 +219,7 @@ 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]
8%|7 | 1.08M/13.6M [00:00<00:01, 11.3MB/s]
25%|##4 | 3.37M/13.6M [00:00<00:00, 18.6MB/s]
60%|#####9 | 8.09M/13.6M [00:00<00:00, 32.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 38.9MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
5%|5 | 720k/13.6M [00:00<00:01, 7.35MB/s]
14%|#4 | 1.90M/13.6M [00:00<00:01, 10.4MB/s]
29%|##8 | 3.89M/13.6M [00:00<00:00, 15.1MB/s]
53%|#####2 | 7.16M/13.6M [00:00<00:00, 22.6MB/s]
93%|#########2| 12.5M/13.6M [00:00<00:00, 34.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 27.5MB/s]
@@ -399,7 +399,7 @@ 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)
- 90.3425 90.3195 91.6169 90.2092 0.1534
+ 90.6644 90.6345 91.3037 90.3919 0.1489
@@ -448,7 +448,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.417 seconds)
+ **Total running time of the script:** ( 1 minutes 11.992 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 52e2174e0..4ddd0e57b 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
@@ -426,7 +426,7 @@ 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)
- 119.5414 119.2088 124.5235 118.2099 0.8757
+ 121.2662 121.2485 122.7286 119.9012 0.4946
@@ -463,7 +463,7 @@ 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 53.010 seconds)
+ **Total running time of the script:** ( 1 minutes 54.689 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 2443d2cd9..d8be347a2 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -254,7 +254,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 9.100 seconds)
+ **Total running time of the script:** ( 1 minutes 16.113 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 e1a4deec5..42d8a3e9d 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
@@ -157,7 +157,7 @@ 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]
2%|2 | 2976/132723 [00:00<00:04, 29676.40KB/s]
7%|6 | 8962/132723 [00:00<00:02, 47407.99KB/s]
13%|#3 | 17399/132723 [00:00<00:01, 64271.59KB/s]
20%|#9 | 25883/132723 [00:00<00:01, 72384.64KB/s]
26%|##5 | 34303/132723 [00:00<00:01, 76642.35KB/s]
32%|###2 | 42841/132723 [00:00<00:01, 79610.67KB/s]
38%|###8 | 50803/132723 [00:00<00:01, 72449.93KB/s]
45%|####4 | 59367/132723 [00:00<00:00, 76381.60KB/s]
51%|##### | 67109/132723 [00:01<00:01, 57331.19KB/s]
57%|#####6 | 75578/132723 [00:01<00:00, 63946.14KB/s]
62%|######2 | 82656/132723 [00:01<00:00, 53085.12KB/s]
69%|######8 | 91181/132723 [00:01<00:00, 60436.83KB/s]
75%|#######5 | 99785/132723 [00:01<00:00, 66738.63KB/s]
82%|########1 | 108415/132723 [00:01<00:00, 71826.24KB/s]
88%|########8 | 117027/132723 [00:01<00:00, 75696.96KB/s]
95%|#########4
| 125622/132723 [00:01<00:00, 78555.19KB/s]
100%|##########| 132723/132723 [00:01<00:00, 69096.53KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6887/132723 [00:00<00:01, 68865.47KB/s]
11%|#1 | 15208/132723 [00:00<00:01, 77298.26KB/s]
18%|#7 | 23621/132723 [00:00<00:01, 80414.24KB/s]
24%|##4 | 32158/132723 [00:00<00:01, 82366.53KB/s]
31%|### | 40619/132723 [00:00<00:01, 83173.94KB/s]
37%|###6 | 49005/132723 [00:00<00:01, 83405.05KB/s]
43%|####3 | 57456/132723 [00:00<00:00, 83765.05KB/s]
50%|####9 | 65978/132723 [00:00<00:00, 84226.39KB/s]
56%|#####6 | 74412/132723 [00:00<00:00, 84258.79KB/s]
63%|######2 | 82962/132723 [00:01<00:00, 84640.17KB/s]
69%|######8 | 91427/132723 [00:01<00:00, 83859.82KB/s]
75%|#######5 | 99867/132723 [00:01<00:00, 84018.68KB/s]
82%|########1 | 108339/132723 [00:01<00:00, 84228.55KB/s]
88%|########8 | 116845/132723 [00:01<00:00, 84476.61KB/s]
94%|#########4| 125314/132723 [00:01<00:00, 84539.78KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83194.44KB/s]
@@ -240,7 +240,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 22.105 seconds)
+ **Total running time of the script:** ( 2 minutes 31.938 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 f07308f68..16c6d84b5 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
@@ -5,22 +5,22 @@
Computation times
=================
-**11:25.263** total execution time for **how_to_deploy_models** files:
+**11:02.773** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:00.945 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:13.460 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:22.105 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:31.938 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 02:09.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:54.689 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:53.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:16.113 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.417 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.992 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.481 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:31.259 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.200 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.317 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
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 11988a824..8c34c0c82 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
@@ -463,7 +463,7 @@ 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.zip005f383d-1a9f-4ad9-9052-dbf78ff4b965 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipe34aee3e-1522-4d34-b1c8-0016884e62e9 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -577,7 +577,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
/workspace/python/tvm/driver/build_module.py:268: 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. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm 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 875c91837..f3ba6f288 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:40.453** total execution time for **how_to_extend_tvm** files:
+**00:43.278** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.311 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:39.810 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.213 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.461 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.922 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.001 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
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 4929f9124..132bf71c3 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
@@ -215,10 +215,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6512us [6512us] (45.66%; 45.66%)
- FoldScaleAxis: 7749us [5us] (54.34%; 54.34%)
- FoldConstant: 7743us [1598us] (54.30%; 99.93%)
- InferType: 6145us [6145us] (43.09%; 79.36%)
+ InferType: 7577us [7577us] (45.84%; 45.84%)
+ FoldScaleAxis: 8953us [8us] (54.16%; 54.16%)
+ FoldConstant: 8944us [1693us] (54.11%; 99.91%)
+ InferType: 7251us [7251us] (43.87%; 81.07%)
@@ -257,10 +257,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6190us [6190us] (45.05%; 45.05%)
- FoldScaleAxis: 7552us [5us] (54.95%; 54.95%)
- FoldConstant: 7547us [1537us] (54.92%; 99.94%)
- InferType: 6010us [6010us] (43.73%; 79.63%)
+ InferType: 7386us [7386us] (44.77%; 44.77%)
+ FoldScaleAxis: 9111us [8us] (55.23%; 55.23%)
+ FoldConstant: 9102us [1859us] (55.18%; 99.91%)
+ InferType: 7243us [7243us] (43.91%; 79.57%)
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 7d4988f60..fbcc9b39d 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
@@ -327,7 +327,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.322227 ms
+ Convolution: 44.967277 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 e34525b9c..6b6b06ff1 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
@@ -658,7 +658,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 9.576298 ms
+ conv2d with tensor core: 10.325996 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 89ed894cb..a3106d21d 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -130,8 +130,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019334
- Baseline: 3.329745
+ Numpy running time: 0.020135
+ Baseline: 3.540702
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.314159
+ Opt1: 0.329501
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.342030
+ Opt2: 0.347252
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118273
+ Opt3: 0.140813
@@ -550,7 +550,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109320
+ Opt4: 0.113586
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110013
+ Opt5: 0.115268
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.143740
+ Opt6: 0.147877
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 6b58b1a25..9fe517106 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.566** total execution time for **how_to_optimize_operators** files:
+**00:36.169** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.185 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.745 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.336 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.353 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.045 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.072 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
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 64a0edcec..a2172fdd8 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
@@ -5,18 +5,18 @@
Computation times
=================
-**05:10.550** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:37.006** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:32.501 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:50.626 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:20.510 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:24.319 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:43.432 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.138 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:16.676 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.580 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.828 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.311 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.603 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.032 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
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 8d635efb8..aec488d5b 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
@@ -239,199 +239,413 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [784]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [128]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[(threadIdx.x_1*42)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*14), 27)) && (floormod((threadIdx.x_1*42), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*14), 27)*49)) + (floordiv(floormod((threadIdx.x_1*14), 27), 3)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*14), 27)) && (floormod(((threadIdx.x_1*42) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*14), 27)*49)) + (floordiv(floormod((threadIdx.x_1*14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*14), 27)) && (floormod(((threadIdx.x_1*42) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*14), 27)*49)) + (floordiv(floormod((threadIdx.x_1*14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 1), 27)) && (floormod(((threadIdx.x_1*42) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 1), 27)) && (floormod(((threadIdx.x_1*42) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 1), 27)) && (floormod(((threadIdx.x_1*42) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 2), 27)) && (floormod(((threadIdx.x_1*42) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 2), 27)) && (floormod(((threadIdx.x_1*42) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 2), 27)) && (floormod(((threadIdx.x_1*42) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)) && (floormod(((threadIdx.x_1*42) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)) && (floormod(((threadIdx.x_1*42) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)) && (floormod(((threadIdx.x_1*42) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 4), 27)) && (floormod(((threadIdx.x_1*42) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 4), 27)) && (floormod(((threadIdx.x_1*42) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 4), 27)) && (floormod(((threadIdx.x_1*42) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 5), 27)) && (floormod(((threadIdx.x_1*42) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 5), 27)) && (floormod(((threadIdx.x_1*42) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 5), 27)) && (floormod(((threadIdx.x_1*42) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 18)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)) && (floormod(((threadIdx.x_1*42) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 19)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)) && (floormod(((threadIdx.x_1*42) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 20)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)) && (floormod(((threadIdx.x_1*42) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 7), 27)) && (floormod(((threadIdx.x_1*42) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 7), 27)) && (floormod(((threadIdx.x_1*42) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 7), 27)) && (floormod(((threadIdx.x_1*42) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 24)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 8), 27)) && (floormod(((threadIdx.x_1*42) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 25)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 8), 27)) && (floormod(((threadIdx.x_1*42) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 26)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 8), 27)) && (floormod(((threadIdx.x_1*42) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 27)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)) && (floormod(((threadIdx.x_1*42) + 27), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 28)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)) && (floormod(((threadIdx.x_1*42) + 28), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 29)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)) && (floormod(((threadIdx.x_1*42) + 29), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 30)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 10), 27)) && (floormod(((threadIdx.x_1*42) + 30), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 31)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 10), 27)) && (floormod(((threadIdx.x_1*42) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 32)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 10), 27)) && (floormod(((threadIdx.x_1*42) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 33)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 11), 27)) && (floormod(((threadIdx.x_1*42) + 33), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 34)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 11), 27)) && (floormod(((threadIdx.x_1*42) + 34), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 35)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 11), 27)) && (floormod(((threadIdx.x_1*42) + 35), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 36)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)) && (floormod(((threadIdx.x_1*42) + 36), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 37)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)) && (floormod(((threadIdx.x_1*42) + 37), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 38)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)) && (floormod(((threadIdx.x_1*42) + 38), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 39)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 13), 27)) && (floormod(((threadIdx.x_1*42) + 39), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 40)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 13), 27)) && (floormod(((threadIdx.x_1*42) + 40), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 41)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 13), 27)) && (floormod(((threadIdx.x_1*42) + 41), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 28), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 84)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 84), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 140)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 140), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 68), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 196), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 252)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 252), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (yy.outer.inner: int32, 0, 7) {
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 17)]))
- }
- }
+ for (rc.outer.outer: int32, 0, 32) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [784], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 188)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 580)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [128], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9))]
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 189)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 385)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 581)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 1)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 190)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 386)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 582)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 2)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 195)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 391)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 587)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 3)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = data[((rc.outer.outer*784) + threadIdx.x_1)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = data[(((rc.outer.outer*784) + threadIdx.x_1) + 196)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = data[(((rc.outer.outer*784) + threadIdx.x_1) + 392)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = data[(((rc.outer.outer*784) + threadIdx.x_1) + 588)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 4)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 197)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 393)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 589)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 5)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 202)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 398)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 594)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 6)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 203)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 399)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 595)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 7)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 204)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 400)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 596)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 8)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*196) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*4) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -486,7 +700,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.311 ms
+ Execution time of this operator: 0.315 ms
@@ -534,33 +748,33 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
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_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
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_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
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=7)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_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=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_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_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ 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_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=1)
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=4)
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=7)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_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=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -583,14 +797,14 @@ 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=28)
+ 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=196)
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=42)
+ 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=28)
+ 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=196)
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", 64)
+ 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, "unroll_explicit", True)
CUDA source code:
@@ -608,184 +822,385 @@ 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__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[288];
+ extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[784];
+ __shared__ float kernel_shared[128];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[(((int)threadIdx.x) * 42)] = (((((3 <= ((((int)threadIdx.x) * 14) % 27)) && (((((int)threadIdx.x) * 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 14) / 27) * 49)) + ((((((int)threadIdx.x) * 14) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 1)] = (((((3 <= ((((int)threadIdx.x) * 14) % 27)) && ((((((int)threadIdx.x) * 42) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 14) / 27) * 49)) + ((((((int)threadIdx.x) * 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 2)] = (((((3 <= ((((int)threadIdx.x) * 14) % 27)) && ((((((int)threadIdx.x) * 42) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 14) / 27) * 49)) + ((((((int)threadIdx.x) * 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 3)] = (((((3 <= (((((int)threadIdx.x) * 14) + 1) % 27)) && ((((((int)threadIdx.x) * 42) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 4)] = (((((3 <= (((((int)threadIdx.x) * 14) + 1) % 27)) && ((((((int)threadIdx.x) * 42) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 5)] = (((((3 <= (((((int)threadIdx.x) * 14) + 1) % 27)) && ((((((int)threadIdx.x) * 42) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 6)] = (((((3 <= (((((int)threadIdx.x) * 14) + 2) % 27)) && ((((((int)threadIdx.x) * 42) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 7)] = (((((3 <= (((((int)threadIdx.x) * 14) + 2) % 27)) && ((((((int)threadIdx.x) * 42) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 8)] = (((((3 <= (((((int)threadIdx.x) * 14) + 2) % 27)) && ((((((int)threadIdx.x) * 42) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 42) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 42) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 42) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 12)] = (((((3 <= (((((int)threadIdx.x) * 14) + 4) % 27)) && ((((((int)threadIdx.x) * 42) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 13)] = (((((3 <= (((((int)threadIdx.x) * 14) + 4) % 27)) && ((((((int)threadIdx.x) * 42) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 14)] = (((((3 <= (((((int)threadIdx.x) * 14) + 4) % 27)) && ((((((int)threadIdx.x) * 42) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 15)] = (((((3 <= (((((int)threadIdx.x) * 14) + 5) % 27)) && ((((((int)threadIdx.x) * 42) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 16)] = (((((3 <= (((((int)threadIdx.x) * 14) + 5) % 27)) && ((((((int)threadIdx.x) * 42) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 17)] = (((((3 <= (((((int)threadIdx.x) * 14) + 5) % 27)) && ((((((int)threadIdx.x) * 42) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 18)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 42) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 19)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 42) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 20)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 42) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 21)] = (((((3 <= (((((int)threadIdx.x) * 14) + 7) % 27)) && ((((((int)threadIdx.x) * 42) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 22)] = (((((3 <= (((((int)threadIdx.x) * 14) + 7) % 27)) && ((((((int)threadIdx.x) * 42) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 188)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 580)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9))];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 23)] = (((((3 <= (((((int)threadIdx.x) * 14) + 7) % 27)) && ((((((int)threadIdx.x) * 42) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 24)] = (((((3 <= (((((int)threadIdx.x) * 14) + 8) % 27)) && ((((((int)threadIdx.x) * 42) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 25)] = (((((3 <= (((((int)threadIdx.x) * 14) + 8) % 27)) && ((((((int)threadIdx.x) * 42) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 26)] = (((((3 <= (((((int)threadIdx.x) * 14) + 8) % 27)) && ((((((int)threadIdx.x) * 42) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 27)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 42) + 27) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 28)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 42) + 28) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 29)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 42) + 29) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 30)] = (((((3 <= (((((int)threadIdx.x) * 14) + 10) % 27)) && ((((((int)threadIdx.x) * 42) + 30) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 31)] = (((((3 <= (((((int)threadIdx.x) * 14) + 10) % 27)) && ((((((int)threadIdx.x) * 42) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 32)] = (((((3 <= (((((int)threadIdx.x) * 14) + 10) % 27)) && ((((((int)threadIdx.x) * 42) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 33)] = (((((3 <= (((((int)threadIdx.x) * 14) + 11) % 27)) && ((((((int)threadIdx.x) * 42) + 33) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 34)] = (((((3 <= (((((int)threadIdx.x) * 14) + 11) % 27)) && ((((((int)threadIdx.x) * 42) + 34) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 35)] = (((((3 <= (((((int)threadIdx.x) * 14) + 11) % 27)) && ((((((int)threadIdx.x) * 42) + 35) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 36)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 42) + 36) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 189)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 385)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 581)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 1)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 37)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 42) + 37) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 190)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 386)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 582)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 2)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 38)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 42) + 38) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 195)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 391)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 587)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 3)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 39)] = (((((3 <= (((((int)threadIdx.x) * 14) + 13) % 27)) && ((((((int)threadIdx.x) * 42) + 39) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = data[((rc_outer_outer * 784) + ((int)threadIdx.x))];
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 196)];
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 392)];
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 588)];
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 4)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 40)] = (((((3 <= (((((int)threadIdx.x) * 14) + 13) % 27)) && ((((((int)threadIdx.x) * 42) + 40) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 197)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 589)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 5)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 41)] = (((((3 <= (((((int)threadIdx.x) * 14) + 13) % 27)) && ((((((int)threadIdx.x) * 42) + 41) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 202)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 398)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 594)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 6)];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 18432) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 28)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 28) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 84)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 84) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 140)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 140) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 68) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 52) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 252)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 252) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36)];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 203)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 399)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 595)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 7)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 17)]));
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 204)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 400)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 596)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 8)];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 4) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -847,7 +1262,7 @@ 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 32.501 seconds)
+ **Total running time of the script:** ( 2 minutes 50.626 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
index 4b1db348f..d52133309 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
@@ -646,7 +646,7 @@ 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)
- 9.8249 9.8201 9.8735 9.7811 0.0379
+ 9.8018 9.7943 9.8533 9.7577 0.0394
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 cebc831f2..eec2e962f 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
@@ -665,7 +665,7 @@ 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)
- 752.2819 751.9914 752.8943 751.9599 0.4333
+ 781.6611 781.5751 782.7018 780.7064 0.8169
@@ -693,7 +693,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.510 seconds)
+ **Total running time of the script:** ( 1 minutes 24.319 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 12cf8464f..6e927301f 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
@@ -396,80 +396,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[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 (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [128], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder[((((i0.outer*2048) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
- }
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_2: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
+ compute[ramp(cse_var_2, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -525,7 +475,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.699 ms
+ Execution time of this operator: 1.312 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 f3dad7231..1ac0c3114 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:43.710** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.485** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.677 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:44.450 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.004 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 48126a4aa..2c69649d3 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
@@ -879,8 +879,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 96.72/96.72 result: MeasureResult(costs=(0.002393513375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7802348136901855, timestamp=1656432764.1831858) [('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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 92.66/92.66 result: MeasureResult(costs=(0.0024983592916666664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8174035549163818, timestamp=1656435149.146044) [('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: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,7 +1003,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,7 +1126,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,7 +1249,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/92.66 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
@@ -1267,7 +1267,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/96.72 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1390,7 +1390,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1513,7 +1513,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1636,7 +1636,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1759,7 +1759,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1882,7 +1882,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2005,7 +2005,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2128,7 +2128,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2251,7 +2251,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2339,7 +2339,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f348964bfa2
+ 12: 0x00007f78e1d6cfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2404,7 +2404,7 @@ 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: 143.91/143.91 result: MeasureResult(costs=(0.0016086114285714284,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.156287431716919, timestamp=1656432790.550082) [('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: 144.91/144.91 result: MeasureResult(costs=(0.00159756869,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.479034185409546, timestamp=1656435175.3001082) [('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
@@ -2461,7 +2461,7 @@ 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
Finish loading 20 records
- Time cost of this operator: 0.002076
+ Time cost of this operator: 0.002015
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 c8fa5b490..e0c00ded2 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
@@ -328,10 +328,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.1 98.777 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.982 0.935 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.919 0.288 (1, 1, 10, 10, 3) 1 1
- Total_time - 319.002 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.4 98.712 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.169 1.001 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 0.286 (1, 1, 10, 10, 3) 1 1
+ Total_time - 316.475 - - - -
@@ -397,10 +397,10 @@ 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 319.8 99.104 (1, 3, 10, 10, 2) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.08 0.644 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.813 0.252 (1, 3, 10, 10, 1) 1 1
- Total_time - 322.692 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 193.3 98.591 (1, 1, 10, 10, 6) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.948 0.994 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.814 0.415 (1, 3, 10, 10, 1) 1 1
+ Total_time - 196.062 - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 3b7c02ea0..42020479c 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpscudv4x_/images/random'
+ '/tmp/tmpe4lzkuo7/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpscudv4x_/images/target contains 8144 images
- /tmp/tmpscudv4x_/images/random contains 5000 images
+ /tmp/tmpe4lzkuo7/images/target contains 8144 images
+ /tmp/tmpe4lzkuo7/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2340 - accuracy: 0.9209 - val_loss: 0.1365 - val_accuracy: 0.9600
+ 328/328 - 56s - loss: 0.2139 - accuracy: 0.9265 - val_loss: 0.1406 - val_accuracy: 0.9585
Epoch 2/3
- 328/328 - 52s - loss: 0.1023 - accuracy: 0.9611 - val_loss: 0.1142 - val_accuracy: 0.9637
+ 328/328 - 53s - loss: 0.0946 - accuracy: 0.9640 - val_loss: 0.1143 - val_accuracy: 0.9622
Epoch 3/3
- 328/328 - 52s - loss: 0.0727 - accuracy: 0.9736 - val_loss: 0.1176 - val_accuracy: 0.9615
+ 328/328 - 53s - loss: 0.0644 - accuracy: 0.9750 - val_loss: 0.1077 - val_accuracy: 0.9615
- <keras.callbacks.History object at 0x7fa684136d50>
+ <keras.callbacks.History object at 0x7f70e1793910>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 9 minutes 4.481 seconds)
+ **Total running time of the script:** ( 7 minutes 59.379 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index ef1e481de..4fa3c1701 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
@@ -5,14 +5,14 @@
Computation times
=================
-**09:51.623** total execution time for **how_to_work_with_microtvm** files:
+**08:49.433** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 09:04.481 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 07:59.379 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.578 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:46.244 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.563 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.810 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
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 23645a6c7..b11e80941 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:11.592** total execution time for **how_to_work_with_relay** files:
+**00:10.272** total execution time for **how_to_work_with_relay** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:08.647 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.559 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.619 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
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 40df5d82d..9ba694249 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
@@ -259,7 +259,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fa5e7d8af80>
+ <function my_cuda_math_rule at 0x7f7062f893b0>
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 5d5d5db87..cf664fa9a 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
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.124** total execution time for **how_to_work_with_schedules** files:
+**00:04.314** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.934 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.973 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.956 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.061 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.537 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.554 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.523 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.106 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.038 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.013 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.014 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 05f66fda4..652cbff07 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -346,7 +346,7 @@ 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/tmpxp2lxik8/input0.cc'\nsource_filename = \"/tmp/tmpxp2lxik8/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/tmpxx53k_i6/input0.cc'\nsource_filename = \"/tmp/tmpxx53k_i6/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index d944d502a..c22e58f6a 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:20.988** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.494** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.982 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.488 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
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 450f87632..cb1c106b2 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.92s!
+ resnet18_v1 inference graph built in 24.72s!
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 3a779a7a9..bd266ab43 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.82s!
+ yolov3-tiny inference graph built in 17.09s!
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 46f68943e..bdd80499c 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
@@ -5,10 +5,10 @@
Computation times
=================
-**01:30.864** total execution time for **topic_vta_tutorials_frontend** files:
+**01:34.796** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.752 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.419 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.112 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.377 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
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 e1ec59f2a..9be53c218 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.229** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.331** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.816 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.911 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.413 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.420 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 921c29971..bb0ad02a3 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.756** total execution time for **topic_vta_tutorials** files:
+**00:00.778** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.407 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.406 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.350 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.372 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 9eb2f9a84..84db9678b 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -327,7 +327,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.361 ms
+ Execution time of this operator: 96.466 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 6320c059f..2a2c0f0ed 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -449,16 +449,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.54/9.54 result: MeasureResult(costs=(0.0281370082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5838139057159424, timestamp=1656431544.0756063) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.91/9.54 result: MeasureResult(costs=(0.09230103840000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6288020610809326, timestamp=1656431546.2400708) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.75/11.75 result: MeasureResult(costs=(0.022836872799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5916013717651367, timestamp=1656431546.8131716) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.46/11.75 result: MeasureResult(costs=(0.1844247434,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0677573680877686, timestamp=1656431550.451093) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.58/11.75 result: MeasureResult(costs=(0.0749565606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3438076972961426, timestamp=1656431551.9296255) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.82/11.75 result: MeasureResult(costs=(0.1473566616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.479562520980835, timestamp=1656431554.97117) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.86/11.75 result: MeasureResult(costs=(0.3121382228,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.116043329238892, timestamp=1656431560.1299756) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.19/11.75 result: MeasureResult(costs=(0.026338152200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5656037330627441, timestamp=1656431560.715064) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.54/11.75 result: MeasureResult(costs=(0.17431820920000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.891237735748291, timestamp=1656431563.7274027) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.67/11.75 result: MeasureResult(costs=(0.10049530200000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7167799472808838, timestamp=1656431565.5037563) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.71/9.71 result: MeasureResult(costs=(0.027646069999999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5867083072662354, timestamp=1656433966.7181191) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.79/9.71 result: MeasureResult(costs=(0.0961177002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6903934478759766, timestamp=1656433968.4228745) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.58/11.58 result: MeasureResult(costs=(0.0231874504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5625529289245605, timestamp=1656433969.5204566) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.65/11.58 result: MeasureResult(costs=(0.1624127696,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7210912704467773, timestamp=1656433972.853541) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.60/11.58 result: MeasureResult(costs=(0.07464471180000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3431448936462402, timestamp=1656433974.3254597) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.59/11.58 result: MeasureResult(costs=(0.16834135060000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8646767139434814, timestamp=1656433977.2320302) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.83/11.58 result: MeasureResult(costs=(0.3225357506,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.3336381912231445, timestamp=1656433983.1740465) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.59/11.58 result: MeasureResult(costs=(0.027990559200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6055922508239746, timestamp=1656433983.787655) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.56/11.58 result: MeasureResult(costs=(0.1720130958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.860116720199585, timestamp=1656433986.7689433) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.64/11.58 result: MeasureResult(costs=(0.10176397159999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.74306321144104, timestamp=1656433988.5698962) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 76e2537fb..27fdde1cf 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -314,7 +314,7 @@ standard deviation.
.. code-block:: none
- {'mean': 495.8506218799994, 'median': 495.5960244999005, 'std': 0.9961609385082597}
+ {'mean': 505.915253750004, 'median': 505.9168230500063, 'std': 0.8558069739254331}
@@ -550,31 +550,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: 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 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 5.81 s
[Task 1/25] Current/Best: 6.15/ 17.42 GFLOPS | Progress: (8/20) | 9.28 s
[Task 1/25] Current/Best: 11.55/ 22.64 GFLOPS | Progress: (12/20) | 11.70 s
[Task 1/25] Current/Best: 16.69/ 22.71 GFLOPS | Progress: (16/20) | 13.39 s
[Task 1/25] Current/Best: 11.58/ 23.89 GFLOPS | Progress: (20/20) | 15.14 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.21/ 12.95 GFLOPS | Progress: (4/20) | 3.65 s
[Task 2/25] Current/Best: 14.12/ 18.58 GFLOPS | Progress: (8/20) | 4.97 s
[Task 2/25] Current/Best: 20.77/ 20.77 GFLOPS | Progress: (12/20) | 6.29 s
[Task 2/25] Current/Best: 12.44/ 20.77 GFLOPS | Progress: (16/20) | 7.55 s
[Task 2/25] Current/Best: 19.90/ 20.77 GFLOPS | Progress: (20/20) | 9.11 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/ 10.57 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.54/ 16.84 GFLOPS | Progress: (8/20) | 7.84 s
[Task 3/25] Current/Best: 14.87/ 16.84 GFLOPS | Progress: (12/20) | 9.60 s
[Task 3/25] Current/Best: 7.21/ 23.60 GFLOPS | Progress: (16/20) | 11.52 s
[Task 3/25] Current/Best: 12.54/ 23.60 GFLOPS | Progress: (20/20) | 16.08 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 20.44 GFLOPS | Progress: (4/20) | 2.40 s
[Task 4/25] Current/Best: 6.87/ 20.44 GFLOPS | Progress: (8/20) | 6.76 s
[Task 4/25] Current/Best: 22.14/ 22.14 GFLOPS | Progress: (12/20) | 11.33 s
[Task 4/25] Current/Best: 16.38/ 22.14 GFLOPS | Progress: (16/20) | 13.58 s
[Task 4/25] Current/Best: 13.30/ 22.14 GFLOPS | Progress: (20/20) | 15.56 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.53/ 10.31 GFLOPS | Progress: (4/20) | 2.61 s
[Task 5/25] Current/Best: 11.71/ 12.95 GFLOPS | Progress: (8/20) | 4.66 s
[Task 5/25] Current/Best: 9.85/ 18.03 GFLOPS | Progress: (12/20) | 7.79 s
[Task 5/25] Current/Best: 11.81/ 22.60 GFLOPS | Progress: (16/20) | 9.21 s
[Task 5/25] Current/Best: 11.85/ 22.60 GFLOPS | Progress: (20/20) | 11.09 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.22/ 20.75 GFLOPS | Progress: (4/20) | 3.98 s
[Task 6/25] Current/Best: 18.88/ 20.75 GFLOPS | Progress: (8/20) | 5.73 s
[Task 6/25] Current/Best: 13.23/ 20.75 GFLOPS | Progress: (12/20) | 7.65 s
[Task 6/25] Current/Best: 19.93/ 20.75 GFLOPS | Progress: (16/20) | 9.89 s
[Task 6/25] Current/Best: 3.73/ 20.75 GFLOPS | Progress: (20/20) | 12.41 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.22/ 12.94 GFLOPS | Progress: (4/20) | 3.55 s
[Task 7/25] Current/Best: 20.09/ 20.95 GFLOPS | Progress: (8/20) | 5.07 s
[Task 7/25] Current/Best: 15.91/ 20.95 GFLOPS | Progress: (12/20) | 6.97 s
[Task 7/25] Current/Best: 12.20/ 20.95 GFLOPS | Progress: (16/20) | 9.02 s
[Task 7/25] Current/Best: 6.37/ 21.70 GFLOPS | Progress: (20/20) | 11.48 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.08/ 14.24 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.41/ 14.24 GFLOPS | Progress: (8/20) | 7.67 s
[Task 8/25] Current/Best: 12.83/ 14.24 GFLOPS | Progress: (12/20) | 13.85 s
[Task 8/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (16/20) | 15.93 s
[Task 8/25] Current/Best: 19.93/ 19.93 GFLOPS | Progress: (20/20) | 22.44 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.24/ 15.77 GFLOPS | Progress: (4/20) | 11.96 s
[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.72 s
[Task 9/25] Current/Best: 8.21/ 23.41 GFLOPS | Progress: (12/20) | 16.09 s
[Task 9/25] Current/Best: 17.94/ 23.41 GFLOPS | Progress: (16/20) | 18.76 s
[Task 9/25] Current/Best: 8.98/ 23.41 GFLOPS | Progress: (20/20) | 26.46 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.51/ 18.51 GFLOPS | Progress: (4/20) | 2.59 s
[Task 10/25] Current/Best: 15.57/ 18.51 GFLOPS | Progress: (8/20) | 4.17 s
[Task 10/25] Current/Best: 12.60/ 18.94 GFLOPS | Progress: (12/20) | 5.71 s
[Task 10/25] Current/Best: 19.07/ 20.33 GFLOPS | Progress: (16/20) | 6.82 s
[Task 10/25] Current/Best: 8.87/ 20.33 GFLOPS | Progress: (20/20
) | 8.35 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.31/ 18.10 GFLOPS | Progress: (4/20) | 3.35 s
[Task 11/25] Current/Best: 16.84/ 18.10 GFLOPS | Progress: (8/20) | 6.09 s
[Task 11/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (12/20) | 8.15 s
[Task 11/25] Current/Best: 13.39/ 21.14 GFLOPS | Progress: (16/20) | 10.88 s
[Task 11/25] Current/Best: 19.41/ 21.14 GFLOPS | Progress: (20/20) | 12.89 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.80/ 18.23 GFLOPS | Progress: (4/20) | 5.43 s
[Task 12/25] Current/Best: 5.20/ 18.23 GFLOPS | Progress: (8/20) | 9.16 s
[Task 12/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (12/20) | 11.18 s
[Task 12/25] Current/Best: 15.09/ 18.97 GFLOPS | Progress: (16/20) | 13.96 s
[Task 12/25] Current/Best: 15.15/ 18.97 GFLOPS | Progress: (20/20) | 15.88 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.72/ 17.33 GFLOPS | Progress: (4/20) | 3.65 s
[Task 13/25] Current/Best: 16.02/ 20.73 GFLOPS | Progress: (8/20) | 6.11 s
[Task 13/25] Current/Best: 19.35/ 21.42 GFLOPS | Progress: (12/20) | 9.00 s
[Task 13/25] Current/Best: 12.22/ 21.42 GFLOPS | Progress: (16/20) | 12.40 s
[Task 13/25] Current/Best: 18.78/ 21.42 GFLOPS | Progress: (20/20) | 14.61 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.54/ 13.54 GFLOPS | Progress: (4/20) | 3.34 s
[Task 14/25] Current/Best: 6.07/ 13.54 GFLOPS | Progress: (8/20) | 5.50 s
[Task 14/25] Current/Best: 20.30/ 20.30 GFLOPS | Progress: (12/20) | 8.07 s
[Task 14/25] Current/Best: 16.56/ 20.30 GFLOPS | Progress: (16/20) | 9.71 s Done.
-
[Task 14/25] Current/Best: 17.27/ 20.30 GFLOPS | Progress: (20/20) | 11.46 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.14/ 17.61 GFLOPS | Progress: (4/20) | 2.75 s
[Task 15/25] Current/Best: 14.35/ 18.00 GFLOPS | Progress: (8/20) | 4.04 s
[Task 15/25] Current/Best: 10.40/ 22.28 GFLOPS | Progress: (12/20) | 6.10 s
[Task 15/25] Current/Best: 20.43/ 22.28 GFLOPS | Progress: (16/20) | 9.27 s
[Task 15/25] Current/Best: 9.63/ 22.28 GFLOPS | Progress: (20/20) | 10.30 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (4/20) | 2.95 s
[Task 16/25] Current/Best: 3.04/ 20.62 GFLOPS | Progress: (8/20) | 4.56 s
[Task 16/25] Current/Best: 19.25/ 20.62 GFLOPS | Progress: (12/20) | 5.78 s
[Task 16/25] Current/Best: 17.68/ 20.62 GFLOPS | Progress: (16/20) |
7.12 s
[Task 16/25] Current/Best: 10.08/ 20.62 GFLOPS | Progress: (20/20) | 9.19 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.88/ 18.77 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.44/ 23.02 GFLOPS | Progress: (8/20) | 7.60 s
[Task 17/25] Current/Best: 16.50/ 23.02 GFLOPS | Progress: (12/20) | 9.64 s
[Task 17/25] Current/Best: 16.81/ 23.02 GFLOPS | Progress: (16/20) | 11.79 s
[Task 17/25] Current/Best: 10.03/ 23.02 GFLOPS | Progress: (20/20) | 13.92 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.22/ 17.40 GFLOPS | Progress: (4/20) | 3.72 s
[Task 18/25] Current/Best: 10.57/ 19.88 GFLOPS | Progress: (8/20) | 7.16 s
[Task 18/25] Current/Best: 18.89/ 19.88 GFLOPS | Progress: (12/20) | 9.11 s
[Task 18/25] Current/Best: 9.86/ 19.88 GFLOPS | Progress: (16/20) | 12.73 s
[Task 18/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (20/20) | 14.26 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.18/ 20.18 GFLOPS | Progress: (4/20) | 6.08 s
[Task 19/25] Current/Best: 2.61/ 20.18 GFLOPS | Progress: (8/20) | 9.33 s
[Task 19/25] Current/Best: 19.45/ 20.47 GFLOPS | Progress: (12/20) | 12.11 s
[Task 19/25] Current/Best: 14.80/ 21.32 GFLOPS | Progress: (16/20) | 14.91 s
[Task 19/25] Current/Best: 2.70/ 23.05 GFLOPS | Progress: (20/20) | 17.69 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.02/ 14.93 GFLOPS | Progress: (4/20) | 3.37 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (4/20) | 6.57 s
[Task 1/25] Current/Best: 6.15/ 17.31 GFLOPS | Progress: (8/20) | 9.66 s
[Task 1/25] Current/Best: 11.45/ 22.40 GFLOPS | Progress: (12/20) | 12.27 s
[Task 1/25] Current/Best: 16.49/ 22.42 GFLOPS | Progress: (16/20) | 14.02 s
[Task 1/25] Current/Best: 11.54/ 23.54 GFLOPS | Progress: (20/20) | 15.82 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.89/ 12.76 GFLOPS | Progress: (4/20) | 4.13 s
[Task 2/25] Current/Best: 14.04/ 17.26 GFLOPS | Progress: (8/20) | 5.49 s
[Task 2/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 6.86 s
[Task 2/25] Current/Best: 12.74/ 20.66 GFLOPS | Progress: (16/20) | 8.20 s
[Task 2/25] Current/Best: 19.55/ 20.66 GFLOPS | Progress: (20/20) | 9.83 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.53 GFLOPS | Progress: (4/20) | 5.96 s
[Task 3/25] Current/Best: 15.50/ 16.85 GFLOPS | Progress: (8/20) | 7.92 s
[Task 3/25] Current/Best: 14.81/ 16.85 GFLOPS | Progress: (12/20) | 9.67 s
[Task 3/25] Current/Best: 7.20/ 23.66 GFLOPS | Progress: (16/20) | 11.61 s
[Task 3/25] Current/Best: 12.54/ 23.66 GFLOPS | Progress: (20/20) | 16.26 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.50/ 20.16 GFLOPS | Progress: (4/20) | 2.52 s
[Task 4/25] Current/Best: 6.85/ 20.16 GFLOPS | Progress: (8/20) | 7.06 s
[Task 4/25] Current/Best: 21.59/ 21.59 GFLOPS | Progress: (12/20) | 11.84 s
[Task 4/25] Current/Best: 17.22/ 21.59 GFLOPS | Progress: (16/20) | 14.15 s
[Task 4/25] Current/Best: 13.03/ 21.59 GFLOPS | Progress: (20/20) | 16.10 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.03/ 10.02 GFLOPS | Progress: (4/20) | 2.70 s
[Task 5/25] Current/Best: 11.34/ 12.71 GFLOPS | Progress: (8/20) | 4.83 s
[Task 5/25] Current/Best: 9.44/ 17.04 GFLOPS | Progress: (12/20) | 7.89 s
[Task 5/25] Current/Best: 11.21/ 22.32 GFLOPS | Progress: (16/20) | 9.35 s
[Task 5/25] Current/Best: 10.48/ 22.32 GFLOPS | Progress: (20/20) | 11.27 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.24/ 20.49 GFLOPS | Progress: (4/20) | 4.14 s
[Task 6/25] Current/Best: 18.66/ 20.49 GFLOPS | Progress: (8/20) | 5.93 s
[Task 6/25] Current/Best: 11.77/ 20.49 GFLOPS | Progress: (12/20) | 7.91 s
[Task 6/25] Current/Best: 19.66/ 20.49 GFLOPS | Progress: (16/20) | 10.19 s
[Task 6/25] Current/Best: 3.67/ 20.49 GFLOPS | Progress: (20/20) | 12.74 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.99/ 12.11 GFLOPS | Progress: (4/20) | 3.69 s
[Task 7/25] Current/Best: 19.70/ 20.88 GFLOPS | Progress: (8/20) | 5.26 s
[Task 7/25] Current/Best: 15.64/ 20.88 GFLOPS | Progress: (12/20) | 7.20 s
[Task 7/25] Current/Best: 12.20/ 20.88 GFLOPS | Progress: (16/20) | 9.30 s
[Task 7/25] Current/Best: 6.43/ 21.72 GFLOPS | Progress: (20/20) | 11.77 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.95/ 14.31 GFLOPS | Progress: (4/20) | 3.01 s
[Task 8/25] Current/Best: 9.59/ 14.31 GFLOPS | Progress: (8/20) | 7.98 s
[Task 8/25] Current/Best: 12.80/ 14.31 GFLOPS | Progress: (12/20) | 14.42 s
[Task 8/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (16/20) | 16.54 s
[Task 8/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (20/20) | 23.29 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.19/ 15.18 GFLOPS | Progress: (4/20) | 12.05 s
[Task 9/25] Current/Best: 22.48/ 22.48 GFLOPS | Progress: (8/20) | 13.91 s
[Task 9/25] Current/Best: 8.21/ 22.48 GFLOPS | Progress: (12/20) | 16.32 s
[Task 9/25] Current/Best: 17.72/ 22.48 GFLOPS | Progress: (16/20) | 19.06 s
[Task 9/25] Current/Best: 8.89/ 22.48 GFLOPS | Progress: (20/20) | 27.25 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.48/ 18.48 GFLOPS | Progress: (4/20) | 2.70 s
[Task 10/25] Current/Best: 15.33/ 18.48 GFLOPS | Progress: (8/20) | 4.33 s
[Task 10/25] Current/Best: 12.18/ 19.07 GFLOPS | Progress: (12/20) | 5.89 s
[Task 10/25] Current/Best: 18.85/ 20.10 GFLOPS | Progress: (16/20) | 7.04 s
[Task 10/25] Current/Best: 8.92/ 20.10 GFLOPS | Progress: (20/20
) | 8.62 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.08/ 17.78 GFLOPS | Progress: (4/20) | 3.46 s
[Task 11/25] Current/Best: 16.10/ 17.78 GFLOPS | Progress: (8/20) | 6.28 s
[Task 11/25] Current/Best: 17.87/ 17.87 GFLOPS | Progress: (12/20) | 8.42 s
[Task 11/25] Current/Best: 13.41/ 21.13 GFLOPS | Progress: (16/20) | 11.43 s
[Task 11/25] Current/Best: 19.10/ 21.46 GFLOPS | Progress: (20/20) | 13.50 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.71/ 18.21 GFLOPS | Progress: (4/20) | 5.60 s
[Task 12/25] Current/Best: 5.20/ 18.21 GFLOPS | Progress: (8/20) | 9.43 s
[Task 12/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 11.45 s
[Task 12/25] Current/Best: 12.44/ 19.05 GFLOPS | Progress: (16/20) | 14.34 s
[Task 12/25] Current/Best: 15.17/ 19.05 GFLOPS | Progress: (20/20) | 16.26 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.84/ 17.27 GFLOPS | Progress: (4/20) | 3.80 s
[Task 13/25] Current/Best: 15.29/ 20.66 GFLOPS | Progress: (8/20) | 6.32 s
[Task 13/25] Current/Best: 19.36/ 20.90 GFLOPS | Progress: (12/20) | 9.30 s
[Task 13/25] Current/Best: 12.17/ 20.90 GFLOPS | Progress: (16/20) | 12.75 s
[Task 13/25] Current/Best: 18.17/ 20.90 GFLOPS | Progress: (20/20) | 15.04 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.27/ 13.27 GFLOPS | Progress: (4/20) | 3.40 s
[Task 14/25] Current/Best: 6.11/ 13.27 GFLOPS | Progress: (8/20) | 5.60 s
[Task 14/25] Current/Best: 19.49/ 19.49 GFLOPS | Progress: (12/20) | 8.21 s
[Task 14/25] Current/Best: 16.17/ 19.49 GFLOPS | Progress: (16/20) | 9.88 s Done.
+
[Task 14/25] Current/Best: 17.13/ 19.49 GFLOPS | Progress: (20/20) | 11.66 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.04/ 17.42 GFLOPS | Progress: (4/20) | 2.85 s
[Task 15/25] Current/Best: 14.32/ 17.87 GFLOPS | Progress: (8/20) | 4.23 s
[Task 15/25] Current/Best: 10.32/ 20.99 GFLOPS | Progress: (12/20) | 6.39 s
[Task 15/25] Current/Best: 20.07/ 20.99 GFLOPS | Progress: (16/20) | 9.68 s
[Task 15/25] Current/Best: 9.56/ 20.99 GFLOPS | Progress: (20/20) | 10.73 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) | 3.07 s
[Task 16/25] Current/Best: 3.03/ 20.17 GFLOPS | Progress: (8/20) | 4.71 s
[Task 16/25] Current/Best: 18.83/ 20.17 GFLOPS | Progress: (12/20) | 5.96 s
[Task 16/25] Current/Best: 17.65/ 20.17 GFLOPS | Progress: (16/20) |
7.33 s
[Task 16/25] Current/Best: 9.80/ 21.65 GFLOPS | Progress: (20/20) | 9.46 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.08/ 18.85 GFLOPS | Progress: (4/20) | 4.84 s
[Task 17/25] Current/Best: 14.37/ 22.73 GFLOPS | Progress: (8/20) | 7.68 s
[Task 17/25] Current/Best: 16.80/ 22.73 GFLOPS | Progress: (12/20) | 9.77 s
[Task 17/25] Current/Best: 16.72/ 22.73 GFLOPS | Progress: (16/20) | 11.95 s
[Task 17/25] Current/Best: 10.02/ 22.73 GFLOPS | Progress: (20/20) | 14.12 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.21/ 17.92 GFLOPS | Progress: (4/20) | 3.86 s
[Task 18/25] Current/Best: 10.55/ 19.57 GFLOPS | Progress: (8/20) | 7.46 s
[Task 18/25] Current/Best: 19.21/ 19.57 GFLOPS | Progress: (12/20) | 9.41 s
[Task 18/25] Current/Best: 9.85/ 19.57 GFLOPS | Progress: (16/20) | 13.17 s
[Task 18/25] Current/Best: 20.70/ 20.70 GFLOPS | Progress: (20/20) | 14.72 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 5.37/ 20.02 GFLOPS | Progress: (4/20) | 6.52 s
[Task 19/25] Current/Best: 2.60/ 20.02 GFLOPS | Progress: (8/20) | 9.84 s
[Task 19/25] Current/Best: 15.73/ 20.21 GFLOPS | Progress: (12/20) | 12.76 s
[Task 19/25] Current/Best: 15.09/ 20.21 GFLOPS | Progress: (16/20) | 15.73 s
[Task 19/25] Current/Best: 2.70/ 22.70 GFLOPS | Progress: (20/20) | 18.54 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.06/ 14.79 GFLOPS | Progress: (4/20) | 3.54 s Done.
Done.
-
[Task 20/25] Current/Best: 10.16/ 14.93 GFLOPS | Progress: (8/20) | 6.80 s
[Task 20/25] Current/Best: 2.31/ 16.12 GFLOPS | Progress: (12/20) | 10.75 s
[Task 20/25] Current/Best: 12.42/ 16.12 GFLOPS | Progress: (16/20) | 14.46 s
[Task 20/25] Current/Best: 13.11/ 21.67 GFLOPS | Progress: (20/20) | 16.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.60 GFLOPS | Progress: (4/20) | 3.25 s
[Task 21/25] Current/Best: 14.50/ 17.60 GFLOPS | Progress: (8/20) | 4.80 s
[Task 21/25] Current/Best: 1.61/ 17.60 GFLOPS | Progress: (12/20) | 6.97 s
[Task 21/25] Current/Best: 17.88/ 17.88 GFLOPS | Progress: (16/20) | 10.43 s
[Task 21/25] Current/Best: 4.46/ 17.88 GFLOPS | Progress: (20/20) | 17.59 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.98 GFLOPS | Progress: (4/20
) | 2.70 s
[Task 22/25] Current/Best: 8.96/ 21.70 GFLOPS | Progress: (8/20) | 4.65 s
[Task 22/25] Current/Best: 19.88/ 21.70 GFLOPS | Progress: (12/20) | 6.95 s
[Task 22/25] Current/Best: 15.20/ 21.70 GFLOPS | Progress: (16/20) | 9.00 s
[Task 22/25] Current/Best: 12.98/ 21.70 GFLOPS | Progress: (20/20) | 10.73 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 16.55/ 20.18 GFLOPS | Progress: (4/20) | 3.30 s
[Task 23/25] Current/Best: 15.47/ 20.18 GFLOPS | Progress: (8/20) | 6.67 s
[Task 23/25] Current/Best: 20.77/ 21.01 GFLOPS | Progress: (12/20) | 8.49 s
[Task 23/25] Current/Best: 6.38/ 21.01 GFLOPS | Progress: (16/20) | 15.45 s
[Task 23/25] Current/Best: 7.67/ 21.01 GFLOPS | Progress: (20/20) | 19.68 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.46/ 8.46 GFLOPS | Progress: (4/20) | 11.81 s
[Task 24/25] Current/Best: 1.96/ 8.46 GFLOPS | Progress: (8/20) | 22.88 s
[Task 24/25] Current/Best: 4.29/ 8.46 GFLOPS | Progress: (12/20) | 34.45 s Done.
+
[Task 20/25] Current/Best: 9.98/ 14.79 GFLOPS | Progress: (8/20) | 7.14 s
[Task 20/25] Current/Best: 2.31/ 16.44 GFLOPS | Progress: (12/20) | 11.15 s
[Task 20/25] Current/Best: 12.32/ 16.44 GFLOPS | Progress: (16/20) | 15.10 s
[Task 20/25] Current/Best: 13.00/ 21.56 GFLOPS | Progress: (20/20) | 17.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.37/ 17.41 GFLOPS | Progress: (4/20) | 3.37 s
[Task 21/25] Current/Best: 14.39/ 17.41 GFLOPS | Progress: (8/20) | 5.00 s
[Task 21/25] Current/Best: 1.61/ 17.41 GFLOPS | Progress: (12/20) | 7.21 s
[Task 21/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (16/20) | 10.78 s
[Task 21/25] Current/Best: 4.45/ 17.91 GFLOPS | Progress: (20/20) | 18.27 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.69/ 16.81 GFLOPS | Progress: (4/20
) | 2.79 s
[Task 22/25] Current/Best: 9.19/ 21.13 GFLOPS | Progress: (8/20) | 4.81 s
[Task 22/25] Current/Best: 19.44/ 21.13 GFLOPS | Progress: (12/20) | 7.18 s
[Task 22/25] Current/Best: 14.55/ 21.13 GFLOPS | Progress: (16/20) | 9.28 s
[Task 22/25] Current/Best: 14.94/ 21.13 GFLOPS | Progress: (20/20) | 11.05 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.19/ 19.96 GFLOPS | Progress: (4/20) | 3.37 s
[Task 23/25] Current/Best: 15.80/ 19.96 GFLOPS | Progress: (8/20) | 6.80 s
[Task 23/25] Current/Best: 20.62/ 21.04 GFLOPS | Progress: (12/20) | 8.66 s
[Task 23/25] Current/Best: 5.55/ 21.04 GFLOPS | Progress: (16/20) | 16.16 s
[Task 23/25] Current/Best: 7.13/ 21.04 GFLOPS | Progress: (20/20) | 20.50 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.24/ 8.24 GFLOPS | Progress: (4/20) | 11.91 s
[Task 24/25] Current/Best: 3.23/ 8.24 GFLOPS | Progress: (8/20) | 23.26 s
[Task 24/25] Current/Best: 3.90/ 8.24 GFLOPS | Progress: (12/20) | 34.02 s Done.
Done.
-
[Task 24/25] Current/Best: 6.90/ 8.74 GFLOPS | Progress: (16/20) | 39.96 s
[Task 24/25] Current/Best: 3.26/ 8.83 GFLOPS | Progress: (20/20) | 45.91 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.52/ 2.92 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 5.56/ 7.83 GFLOPS | Progress: (8/20) | 22.91 s
[Task 25/25] Current/Best: 5.93/ 7.83 GFLOPS | Progress: (12/20) | 34.21 s
[Task 25/25] Current/Best: 5.76/ 9.23 GFLOPS | Progress: (16/20) | 35.97 s
[Task 25/25] Current/Best: 2.88/ 9.23 GFLOPS | Progress: (20/20) | 46.66 s
+
[Task 24/25] Current/Best: 7.09/ 8.25 GFLOPS | Progress: (16/20) | 39.80 s
[Task 24/25] Current/Best: 3.08/ 8.75 GFLOPS | Progress: (20/20) | 46.09 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.52/ 2.58 GFLOPS | Progress: (4/20) | 11.70 s
[Task 25/25] Current/Best: 4.94/ 7.29 GFLOPS | Progress: (8/20) | 23.08 s
[Task 25/25] Current/Best: 5.59/ 7.29 GFLOPS | Progress: (12/20) | 34.43 s
[Task 25/25] Current/Best: 5.45/ 8.57 GFLOPS | Progress: (16/20) | 36.34 s
[Task 25/25] Current/Best: 2.88/ 8.57 GFLOPS | Progress: (20/20) | 47.03 s
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.77566085002036, 'median': 417.7301799499219, 'std': 0.9381233133395673}
- unoptimized: {'mean': 495.8506218799994, 'median': 495.5960244999005, 'std': 0.9961609385082597}
+ optimized: {'mean': 419.95983982000325, 'median': 419.8618299000145, 'std': 1.4574627417621062}
+ unoptimized: {'mean': 505.915253750004, 'median': 505.9168230500063, 'std': 0.8558069739254331}
@@ -759,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 19.583 seconds)
+ **Total running time of the script:** ( 10 minutes 35.123 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 12360ae3b..f3a56eabe 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -269,7 +269,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.332e-07 secs/op
+ 1.27e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index fc5cd9c6e..29054e8dc 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -262,7 +262,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x204ab590)), stage(b, placeholder(b, 0x4775ef0)), 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 [...]
+ [stage(a, placeholder(a, 0x4629810)), stage(b, placeholder(b, 0x21ede770)), 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 [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 925a28ffe..816da6e62 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:02.271** total execution time for **tutorial** files:
+**13:20.666** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:19.583 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:35.123 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.143 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:03.098 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:46.422 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:46.163 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.558 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:29.305 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.930 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.516 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.788 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.728 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.693 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.536 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.154 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.195 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index e2c78e1b3..34ac753e3 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -288,7 +288,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000006
@@ -390,7 +390,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:268: 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. "
- parallel: 0.000007
+ parallel: 0.000006
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.78711999373627e-06 1.0
- naive 5.8932e-06 0.7567881328065211
- parallel 7.051700000000001e-06 0.9055594373365482
- vector 2.4635299999999998e-05 3.1635957863518103
+ numpy 7.010519998402742e-06 1.0
+ naive 5.9013000000000006e-06 0.8417777855771806
+ parallel 6.1149000000000005e-06 0.8722462815016865
+ vector 2.45842e-05 3.5067584152960407
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018628
+ Numpy running time: 0.019532
@@ -983,7 +983,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: 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: 3.410810
+ none: 3.507196
@@ -1088,7 +1088,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: 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. "
- blocking: 0.313466
+ blocking: 0.329147
@@ -1186,7 +1186,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: 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. "
- vectorization: 0.342670
+ vectorization: 0.347269
@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], []),
@@ -1262,7 +1262,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:268: 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. "
- loop permutation: 0.119944
+ loop permutation: 0.136789
@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], []),
@@ -1363,7 +1363,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:268: 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. "
- array packing: 0.111957
+ array packing: 0.111678
@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], []),
@@ -1458,7 +1458,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:268: 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. "
- block caching: 0.110606
+ block caching: 0.114138
@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], []),
@@ -1546,7 +1546,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:268: 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. "
- parallelization: 0.145019
+ parallelization: 0.148607
@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], []),
@@ -1627,13 +1627,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4108103351 1.0
- blocking 0.3134660292 0.09190368223474076
- vectorization 0.3426699868 0.10046585800261257
- loop permutation 0.1199437368 0.0351657597508961
- array packing 0.11195676619999999 0.032824096094665314
- block caching 0.11060611329999999 0.032428104301717844
- parallelization 0.1450192315 0.04251753022079085
+ none 3.5071963054 1.0
+ blocking 0.32914739159999995 0.09384914984462504
+ vectorization 0.347269327 0.09901622172255155
+ loop permutation 0.1367886979 0.03900229299665594
+ array packing 0.1116779582 0.03184251706357309
+ block caching 0.1141378778 0.03254390911174915
+ parallelization 0.14860707099999998 0.04237204252615998
@@ -1675,7 +1675,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.143 seconds)
+ **Total running time of the script:** ( 1 minutes 3.098 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 3b269fb16..47adb8ac4 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-bd49b0846a6f435991a55dec11f5a01169b83b36
+b733aa3ec87a1c5a6e49350bd805e187db1aca70
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 87dd4e495..3f56dac92 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1171e2a2-a280-4ef1-89df-addf44b82fb6 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip69e2df53-adb4-4e31-9e0d-59d4885dd89b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index c57e1607d..3a68876f5 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,98 +427,52 @@ 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<09:08, 79.3kB/s]
- 0%| | 48.0k/41.5M [00:00<05:22, 135kB/s]
- 0%| | 96.0k/41.5M [00:00<03:44, 193kB/s]
- 0%| | 160k/41.5M [00:00<02:55, 247kB/s]
- 1%| | 320k/41.5M [00:00<01:37, 444kB/s]
- 1%|1 | 488k/41.5M [00:01<01:12, 590kB/s]
- 2%|1 | 664k/41.5M [00:01<00:59, 721kB/s]
- 2%|1 | 848k/41.5M [00:01<00:53, 796kB/s]
- 2%|2 | 1.02M/41.5M [00:01<00:50, 845kB/s]
- 3%|2 | 1.21M/41.5M [00:01<00:47, 893kB/s]
- 3%|3 | 1.41M/41.5M [00:02<00:43, 963kB/s]
- 4%|3 | 1.62M/41.5M [00:02<00:40, 1.02MB/s]
- 4%|4 | 1.83M/41.5M [00:02<00:40, 1.04MB/s]
- 5%|4 | 2.05M/41.5M [00:02<00:39, 1.06MB/s]
- 6%|5 | 2.29M/41.5M [00:02<00:36, 1.13MB/s]
- 6%|6 | 2.54M/41.5M [00:03<00:33, 1.21MB/s]
- 7%|6 | 2.80M/41.5M [00:03<00:32, 1.25MB/s]
- 7%|7 | 3.08M/41.5M [00:03<00:31, 1.29MB/s]
- 8%|8 | 3.36M/41.5M [00:03<00:29, 1.34MB/s]
- 9%|8 | 3.66M/41.5M [00:03<00:27, 1.46MB/s]
- 10%|9 | 3.98M/41.5M [00:04<00:25, 1.52MB/s]
- 10%|# | 4.31M/41.5M [00:04<00:25, 1.54MB/s]
- 11%|#1 | 4.60M/41.5M [00:04<00:25, 1.51MB/s]
- 12%|#1 | 4.95M/41.5M [00:04<00:23, 1.66MB/s]
- 13%|#2 | 5.34M/41.5M [00:04<00:21, 1.80MB/s]
- 14%|#3 | 5.73M/41.5M [00:05<00:20, 1.87MB/s]
- 15%|#4 | 6.14M/41.5M [00:05<00:19, 1.93MB/s]
- 16%|#5 | 6.58M/41.5M [00:05<00:17, 2.07MB/s]
- 17%|#6 | 7.04M/41.5M [00:05<00:16, 2.25MB/s]
- 18%|#8 | 7.52M/41.5M [00:05<00:15, 2.32MB/s]
- 19%|#9 | 8.02M/41.5M [00:06<00:14, 2.37MB/s]
- 21%|## | 8.55M/41.5M [00:06<00:13, 2.50MB/s]
- 22%|##1 | 9.10M/41.5M [00:06<00:12, 2.73MB/s]
- 23%|##3 | 9.65M/41.5M [00:06<00:11, 2.82MB/s]
- 25%|##4 | 10.2M/41.5M [00:06<00:11, 2.84MB/s]
- 26%|##5 | 10.8M/41.5M [00:07<00:11, 2.83MB/s]
- 27%|##7 | 11.3M/41.5M [00:07<00:10, 2.95MB/s]
- 29%|##8 | 11.9M/41.5M [00:07<00:10, 3.05MB/s]
- 30%|##9 | 12.4M/41.5M [00:07<00:10, 3.02MB/s]
- 31%|###1 | 13.0M/41.5M [00:07<00:10, 2.95MB/s]
- 33%|###2 | 13.5M/41.5M [00:07<00:08, 3.27MB/s]
- 34%|###3 | 14.0M/41.5M [00:08<00:08, 3.51MB/s]
- 35%|###4 | 14.3M/41.5M [00:08<00:08, 3.36MB/s]
- 35%|###5 | 14.7M/41.5M [00:08<00:09, 2.86MB/s]
- 37%|###6 | 15.2M/41.5M [00:08<00:09, 2.83MB/s]
- 38%|###7 | 15.8M/41.5M [00:08<00:08, 3.28MB/s]
- 39%|###9 | 16.2M/41.5M [00:08<00:07, 3.49MB/s]
- 40%|###9 | 16.6M/41.5M [00:09<00:08, 3.10MB/s]
- 41%|#### | 16.9M/41.5M [00:09<00:09, 2.76MB/s]
- 42%|####2 | 17.5M/41.5M [00:09<00:08, 2.87MB/s]
- 43%|####3 | 18.0M/41.5M [00:09<00:07, 3.37MB/s]
- 44%|####4 | 18.5M/41.5M [00:09<00:07, 3.44MB/s]
- 45%|####5 | 18.8M/41.5M [00:09<00:07, 3.04MB/s]
- 46%|####6 | 19.2M/41.5M [00:09<00:08, 2.81MB/s]
- 48%|####7 | 19.7M/41.5M [00:10<00:06, 3.47MB/s]
- 49%|####8 | 20.2M/41.5M [00:10<00:05, 3.72MB/s]
- 50%|####9 | 20.6M/41.5M [00:10<00:06, 3.18MB/s]
- 50%|##### | 20.9M/41.5M [00:10<00:08, 2.62MB/s]
- 52%|#####1 | 21.5M/41.5M [00:10<00:07, 2.86MB/s]
- 53%|#####3 | 22.1M/41.5M [00:10<00:06, 3.10MB/s]
- 55%|#####4 | 22.7M/41.5M [00:11<00:06, 3.16MB/s]
- 56%|#####6 | 23.3M/41.5M [00:11<00:06, 3.15MB/s]
- 58%|#####7 | 23.9M/41.5M [00:11<00:05, 3.17MB/s]
- 59%|#####9 | 24.6M/41.5M [00:11<00:05, 3.34MB/s]
- 61%|###### | 25.2M/41.5M [00:11<00:04, 3.47MB/s]
- 62%|######2 | 25.8M/41.5M [00:12<00:04, 3.46MB/s]
- 64%|######3 | 26.5M/41.5M [00:12<00:04, 3.42MB/s]
- 65%|######5 | 27.2M/41.5M [00:12<00:04, 3.47MB/s]
- 67%|######7 | 27.8M/41.5M [00:12<00:03, 3.80MB/s]
- 69%|######8 | 28.5M/41.5M [00:12<00:03, 3.85MB/s]
- 70%|####### | 29.2M/41.5M [00:12<00:02, 4.45MB/s]
- 71%|#######1 | 29.7M/41.5M [00:13<00:02, 4.22MB/s]
- 73%|#######2 | 30.1M/41.5M [00:13<00:03, 3.47MB/s]
- 74%|#######3 | 30.7M/41.5M [00:13<00:03, 3.44MB/s]
- 76%|#######5 | 31.4M/41.5M [00:13<00:02, 3.75MB/s]
- 78%|#######7 | 32.2M/41.5M [00:13<00:02, 3.86MB/s]
- 79%|#######9 | 32.9M/41.5M [00:13<00:02, 4.47MB/s]
- 81%|######## | 33.5M/41.5M [00:14<00:01, 4.61MB/s]
- 82%|########1 | 34.0M/41.5M [00:14<00:01, 4.11MB/s]
- 83%|########3 | 34.5M/41.5M [00:14<00:01, 4.48MB/s]
- 85%|########4 | 35.2M/41.5M [00:14<00:01, 4.93MB/s]
- 86%|########5 | 35.7M/41.5M [00:14<00:01, 4.35MB/s]
- 87%|########7 | 36.2M/41.5M [00:14<00:01, 4.49MB/s]
- 89%|########8 | 36.9M/41.5M [00:14<00:00, 4.86MB/s]
- 90%|######### | 37.4M/41.5M [00:14<00:01, 4.14MB/s]
- 92%|#########1| 38.0M/41.5M [00:15<00:00, 4.57MB/s]
- 93%|#########3| 38.7M/41.5M [00:15<00:00, 5.28MB/s]
- 95%|#########4| 39.2M/41.5M [00:15<00:00, 4.77MB/s]
- 96%|#########5| 39.8M/41.5M [00:15<00:00, 4.95MB/s]
- 98%|#########7| 40.6M/41.5M [00:15<00:00, 5.52MB/s]
- 99%|#########9| 41.1M/41.5M [00:15<00:00, 4.65MB/s]
-100%|##########| 41.5M/41.5M [00:15<00:00, 2.77MB/s]
+ 0%| | 16.0k/41.5M [00:00<10:06, 71.7kB/s]
+ 0%| | 48.0k/41.5M [00:00<06:22, 114kB/s]
+ 0%| | 96.0k/41.5M [00:00<04:29, 161kB/s]
+ 0%| | 168k/41.5M [00:00<03:09, 229kB/s]
+ 1%| | 224k/41.5M [00:01<02:53, 250kB/s]
+ 1%|1 | 456k/41.5M [00:01<01:15, 568kB/s]
+ 2%|2 | 904k/41.5M [00:01<00:37, 1.12MB/s]
+ 4%|4 | 1.76M/41.5M [00:01<00:19, 2.17MB/s]
+ 7%|6 | 2.75M/41.5M [00:01<00:13, 2.98MB/s]
+ 9%|9 | 3.79M/41.5M [00:02<00:11, 3.58MB/s]
+ 12%|#1 | 4.88M/41.5M [00:02<00:09, 4.05MB/s]
+ 14%|#4 | 6.01M/41.5M [00:02<00:08, 4.45MB/s]
+ 17%|#7 | 7.20M/41.5M [00:02<00:07, 4.79MB/s]
+ 20%|## | 8.46M/41.5M [00:03<00:06, 5.14MB/s]
+ 24%|##3 | 9.77M/41.5M [00:03<00:06, 5.46MB/s]
+ 27%|##6 | 11.2M/41.5M [00:03<00:05, 5.79MB/s]
+ 30%|### | 12.6M/41.5M [00:03<00:04, 6.94MB/s]
+ 33%|###3 | 13.8M/41.5M [00:03<00:03, 7.98MB/s]
+ 35%|###5 | 14.7M/41.5M [00:03<00:04, 6.62MB/s]
+ 37%|###7 | 15.5M/41.5M [00:04<00:04, 6.76MB/s]
+ 41%|#### | 16.9M/41.5M [00:04<00:03, 8.32MB/s]
+ 43%|####2 | 17.8M/41.5M [00:04<00:03, 6.80MB/s]
+ 45%|####4 | 18.6M/41.5M [00:04<00:04, 5.72MB/s]
+ 48%|####8 | 20.0M/41.5M [00:04<00:03, 6.98MB/s]
+ 51%|##### | 21.1M/41.5M [00:04<00:02, 7.91MB/s]
+ 53%|#####2 | 21.9M/41.5M [00:05<00:03, 6.41MB/s]
+ 55%|#####5 | 22.9M/41.5M [00:05<00:02, 6.79MB/s]
+ 57%|#####7 | 23.7M/41.5M [00:05<00:03, 4.72MB/s]
+ 59%|#####9 | 24.6M/41.5M [00:05<00:03, 4.59MB/s]
+ 62%|######1 | 25.6M/41.5M [00:05<00:03, 4.71MB/s]
+ 64%|######4 | 26.7M/41.5M [00:06<00:03, 4.81MB/s]
+ 67%|######7 | 27.8M/41.5M [00:06<00:02, 4.94MB/s]
+ 70%|######9 | 29.0M/41.5M [00:06<00:02, 5.09MB/s]
+ 73%|#######2 | 30.1M/41.5M [00:06<00:01, 6.10MB/s]
+ 74%|#######4 | 30.8M/41.5M [00:06<00:01, 6.06MB/s]
+ 76%|#######5 | 31.4M/41.5M [00:07<00:02, 4.91MB/s]
+ 78%|#######8 | 32.6M/41.5M [00:07<00:01, 6.01MB/s]
+ 80%|######## | 33.2M/41.5M [00:07<00:01, 6.01MB/s]
+ 82%|########1 | 33.8M/41.5M [00:07<00:01, 4.85MB/s]
+ 85%|########4 | 35.1M/41.5M [00:07<00:01, 5.13MB/s]
+ 88%|########7 | 36.4M/41.5M [00:07<00:00, 6.39MB/s]
+ 89%|########9 | 37.1M/41.5M [00:07<00:00, 6.48MB/s]
+ 91%|######### | 37.7M/41.5M [00:08<00:00, 5.26MB/s]
+ 94%|#########4| 39.0M/41.5M [00:08<00:00, 5.56MB/s]
+ 97%|#########7| 40.4M/41.5M [00:08<00:00, 5.83MB/s]
+100%|##########| 41.5M/41.5M [00:08<00:00, 5.03MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index b6e55e727..ebdcc3f96 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -488,7 +488,7 @@ 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 7.642 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.545 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download sphx-glr-download-python 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 9ab9d952f..e36a51783 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,12 +409,14 @@ 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]
- 3%|2 | 1.18M/44.7M [00:00<00:03, 12.3MB/s]
- 8%|7 | 3.42M/44.7M [00:00<00:02, 18.9MB/s]
- 18%|#7 | 7.91M/44.7M [00:00<00:01, 31.6MB/s]
- 38%|###8 | 17.0M/44.7M [00:00<00:00, 56.8MB/s]
- 79%|#######9 | 35.3M/44.7M [00:00<00:00, 105MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 86.1MB/s]
+ 2%|1 | 824k/44.7M [00:00<00:05, 8.29MB/s]
+ 5%|4 | 2.18M/44.7M [00:00<00:03, 11.8MB/s]
+ 10%|9 | 4.43M/44.7M [00:00<00:02, 17.1MB/s]
+ 18%|#7 | 8.03M/44.7M [00:00<00:01, 25.2MB/s]
+ 31%|###1 | 13.9M/44.7M [00:00<00:00, 38.4MB/s]
+ 44%|####4 | 19.8M/44.7M [00:00<00:00, 46.0MB/s]
+ 68%|######8 | 30.6M/44.7M [00:00<00:00, 68.0MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 58.9MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 87081a9b3..4da231a42 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ 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 5.631 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.088 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index ac4f1bf1f..28a578959 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>06:01.884</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:43.530</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,43 +331,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>01:07.642</p></td>
+<td><p>01:10.545</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>01:05.631</p></td>
+<td><p>01:07.088</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:59.181</p></td>
+<td><p>00:59.807</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:41.708</p></td>
+<td><p>00:36.407</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
-<td><p>00:33.967</p></td>
+<tr class="row-odd"><td><p><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></td>
+<td><p>00:24.723</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:24.130</p></td>
+<td><p>00:24.567</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:23.977</p></td>
+<td><p>00:22.930</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
-<td><p>00:23.170</p></td>
+<tr class="row-even"><td><p><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></td>
+<td><p>00:20.462</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
-<td><p>00:19.814</p></td>
+<tr class="row-odd"><td><p><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></td>
+<td><p>00:14.459</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:02.663</p></td>
+<td><p>00:02.542</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 9d4568d43..9744c9cd2 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3086 16.2930 16.7488 16.1469 0.1674
+ 16.5379 16.5268 16.6690 16.4321 0.0711
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
index b6e235b6f..b20e38995 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,18 +431,19 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|1 | 2.94M/170M [00:00<00:05, 30.5MB/s]
- 5%|5 | 8.88M/170M [00:00<00:03, 49.0MB/s]
- 12%|#1 | 19.5M/170M [00:00<00:02, 77.6MB/s]
- 22%|##1 | 36.9M/170M [00:00<00:01, 119MB/s]
- 33%|###2 | 55.2M/170M [00:00<00:00, 145MB/s]
- 43%|####3 | 73.4M/170M [00:00<00:00, 160MB/s]
- 54%|#####3 | 91.7M/170M [00:00<00:00, 171MB/s]
- 65%|######4 | 110M/170M [00:00<00:00, 177MB/s]
- 76%|#######5 | 128M/170M [00:00<00:00, 182MB/s]
- 86%|########6 | 146M/170M [00:01<00:00, 184MB/s]
- 97%|#########6| 165M/170M [00:01<00:00, 186MB/s]
-100%|##########| 170M/170M [00:01<00:00, 156MB/s]
+ 5%|5 | 8.74M/170M [00:00<00:01, 91.5MB/s]
+ 15%|#4 | 25.0M/170M [00:00<00:01, 138MB/s]
+ 24%|##4 | 41.0M/170M [00:00<00:00, 152MB/s]
+ 34%|###3 | 57.3M/170M [00:00<00:00, 159MB/s]
+ 43%|####3 | 73.3M/170M [00:00<00:00, 162MB/s]
+ 52%|#####2 | 88.8M/170M [00:00<00:00, 155MB/s]
+ 61%|######1 | 104M/170M [00:00<00:00, 145MB/s]
+ 69%|######9 | 118M/170M [00:00<00:00, 139MB/s]
+ 77%|#######7 | 131M/170M [00:00<00:00, 136MB/s]
+ 85%|########4 | 144M/170M [00:01<00:00, 135MB/s]
+ 92%|#########2| 157M/170M [00:01<00:00, 134MB/s]
+100%|##########| 170M/170M [00:01<00:00, 135MB/s]
+100%|##########| 170M/170M [00:01<00:00, 141MB/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').
@@ -537,7 +538,7 @@ 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 0.945 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 13.460 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python 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 6280dbd8c..df64622d8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -472,10 +472,12 @@ 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]
- 8%|7 | 1.08M/13.6M [00:00<00:01, 11.3MB/s]
- 25%|##4 | 3.37M/13.6M [00:00<00:00, 18.6MB/s]
- 60%|#####9 | 8.09M/13.6M [00:00<00:00, 32.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 38.9MB/s]
+ 5%|5 | 720k/13.6M [00:00<00:01, 7.35MB/s]
+ 14%|#4 | 1.90M/13.6M [00:00<00:01, 10.4MB/s]
+ 29%|##8 | 3.89M/13.6M [00:00<00:00, 15.1MB/s]
+ 53%|#####2 | 7.16M/13.6M [00:00<00:00, 22.6MB/s]
+ 93%|#########2| 12.5M/13.6M [00:00<00:00, 34.8MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 27.5MB/s]
</pre></div>
</div>
</div>
@@ -564,7 +566,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<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)
- 90.3425 90.3195 91.6169 90.2092 0.1534
+ 90.6644 90.6345 91.3037 90.3919 0.1489
</pre></div>
</div>
<div class="admonition note">
@@ -603,7 +605,7 @@ 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 8.417 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.992 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python 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 78bf66975..42d6b8daf 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -565,7 +565,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<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)
- 119.5414 119.2088 124.5235 118.2099 0.8757
+ 121.2662 121.2485 122.7286 119.9012 0.4946
</pre></div>
</div>
<div class="admonition note">
@@ -593,7 +593,7 @@ 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 53.010 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 54.689 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python 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 b3badb7da..faef95db1 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 9.100 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.113 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python 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 703a0cc17..1eec2c566 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,23 +436,22 @@ 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]
- 2%|2 | 2976/132723 [00:00<00:04, 29676.40KB/s]
- 7%|6 | 8962/132723 [00:00<00:02, 47407.99KB/s]
- 13%|#3 | 17399/132723 [00:00<00:01, 64271.59KB/s]
- 20%|#9 | 25883/132723 [00:00<00:01, 72384.64KB/s]
- 26%|##5 | 34303/132723 [00:00<00:01, 76642.35KB/s]
- 32%|###2 | 42841/132723 [00:00<00:01, 79610.67KB/s]
- 38%|###8 | 50803/132723 [00:00<00:01, 72449.93KB/s]
- 45%|####4 | 59367/132723 [00:00<00:00, 76381.60KB/s]
- 51%|##### | 67109/132723 [00:01<00:01, 57331.19KB/s]
- 57%|#####6 | 75578/132723 [00:01<00:00, 63946.14KB/s]
- 62%|######2 | 82656/132723 [00:01<00:00, 53085.12KB/s]
- 69%|######8 | 91181/132723 [00:01<00:00, 60436.83KB/s]
- 75%|#######5 | 99785/132723 [00:01<00:00, 66738.63KB/s]
- 82%|########1 | 108415/132723 [00:01<00:00, 71826.24KB/s]
- 88%|########8 | 117027/132723 [00:01<00:00, 75696.96KB/s]
- 95%|#########4| 125622/132723 [00:01<00:00, 78555.19KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 69096.53KB/s]
+ 5%|5 | 6887/132723 [00:00<00:01, 68865.47KB/s]
+ 11%|#1 | 15208/132723 [00:00<00:01, 77298.26KB/s]
+ 18%|#7 | 23621/132723 [00:00<00:01, 80414.24KB/s]
+ 24%|##4 | 32158/132723 [00:00<00:01, 82366.53KB/s]
+ 31%|### | 40619/132723 [00:00<00:01, 83173.94KB/s]
+ 37%|###6 | 49005/132723 [00:00<00:01, 83405.05KB/s]
+ 43%|####3 | 57456/132723 [00:00<00:00, 83765.05KB/s]
+ 50%|####9 | 65978/132723 [00:00<00:00, 84226.39KB/s]
+ 56%|#####6 | 74412/132723 [00:00<00:00, 84258.79KB/s]
+ 63%|######2 | 82962/132723 [00:01<00:00, 84640.17KB/s]
+ 69%|######8 | 91427/132723 [00:01<00:00, 83859.82KB/s]
+ 75%|#######5 | 99867/132723 [00:01<00:00, 84018.68KB/s]
+ 82%|########1 | 108339/132723 [00:01<00:00, 84228.55KB/s]
+ 88%|########8 | 116845/132723 [00:01<00:00, 84476.61KB/s]
+ 94%|#########4| 125314/132723 [00:01<00:00, 84539.78KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83194.44KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -495,7 +494,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.105 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 31.938 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python 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 06cb8901f..8315d2a14 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>11:25.263</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:02.773</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>03:00.945</p></td>
+<td><p>03:13.460</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>02:22.105</p></td>
+<td><p>02:31.938</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
-<td><p>02:09.100</p></td>
+<tr class="row-odd"><td><p><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></td>
+<td><p>01:54.689</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
-<td><p>01:53.010</p></td>
+<tr class="row-even"><td><p><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></td>
+<td><p>01:16.113</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>01:08.417</p></td>
+<td><p>01:11.992</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:29.481</p></td>
+<td><p>00:31.259</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:22.200</p></td>
+<td><p>00:23.317</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
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 0eeb57b96..d7f948813 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -604,7 +604,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip005f383d-1a9f-4ad9-9052-dbf78ff4b965 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.zipe34aee3e-1522-4d34-b1c8-0016884e62e9 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>
@@ -668,7 +668,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm 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 registered 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 91eb469b9..1c9bd48fd 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:40.453</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:43.278</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,19 +331,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:37.311</p></td>
+<td><p>00:39.810</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:02.213</p></td>
+<td><p>00:02.461</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.922</p></td>
+<td><p>00:01.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 610f5bf77..3dd7bcb49 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6512us [6512us] (45.66%; 45.66%)
-FoldScaleAxis: 7749us [5us] (54.34%; 54.34%)
- FoldConstant: 7743us [1598us] (54.30%; 99.93%)
- InferType: 6145us [6145us] (43.09%; 79.36%)
+InferType: 7577us [7577us] (45.84%; 45.84%)
+FoldScaleAxis: 8953us [8us] (54.16%; 54.16%)
+ FoldConstant: 8944us [1693us] (54.11%; 99.91%)
+ InferType: 7251us [7251us] (43.87%; 81.07%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6190us [6190us] (45.05%; 45.05%)
-FoldScaleAxis: 7552us [5us] (54.95%; 54.95%)
- FoldConstant: 7547us [1537us] (54.92%; 99.94%)
- InferType: 6010us [6010us] (43.73%; 79.63%)
+InferType: 7386us [7386us] (44.77%; 44.77%)
+FoldScaleAxis: 9111us [8us] (55.23%; 55.23%)
+ FoldConstant: 9102us [1859us] (55.18%; 99.91%)
+ InferType: 7243us [7243us] (43.91%; 79.57%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 3a0a5429b..e976a1817 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -556,7 +556,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.322227 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 44.967277 ms
</pre></div>
</div>
<div class="sphx-glr-footer 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 a2490762f..e87c619f8 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -898,7 +898,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.576298 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.325996 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 b5812b15e..ae45562c8 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -453,8 +453,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019334
-Baseline: 3.329745
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.020135
+Baseline: 3.540702
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -514,7 +514,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.314159
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.329501
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -581,7 +581,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.342030
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.347252
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -642,7 +642,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118273
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.140813
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -725,7 +725,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109320
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.113586
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -811,7 +811,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110013
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.115268
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -901,7 +901,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.143740
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147877
</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 f5920f7a0..a41cb5a37 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:34.566</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:36.169</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:32.185</p></td>
+<td><p>00:33.745</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:01.336</p></td>
+<td><p>00:01.353</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:01.045</p></td>
+<td><p>00:01.072</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 e4222a7b0..dde9722fc 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>05:10.550</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:37.006</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>02:32.501</p></td>
+<td><p>02:50.626</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>01:20.510</p></td>
+<td><p>01:24.319</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:43.432</p></td>
+<td><p>00:45.138</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:16.676</p></td>
+<td><p>00:18.580</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:08.828</p></td>
+<td><p>00:09.311</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:08.603</p></td>
+<td><p>00:09.032</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 5f6ad83c2..c2c81bb45 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
@@ -486,199 +486,413 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [784]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [128]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[(threadIdx.x_1*42)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*14), 27)) && (floormod((threadIdx.x_1*42), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*14), 27)*49)) + (floordiv(floormod((threadIdx.x_1*14), 27), 3)*7)) + floormod((threadId [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*14), 27)) && (floormod(((threadIdx.x_1*42) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*14), 27)*49)) + (floordiv(floormod((threadIdx.x_1*14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*14), 27)) && (floormod(((threadIdx.x_1*42) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*14), 27)*49)) + (floordiv(floormod((threadIdx.x_1*14), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 1), 27)) && (floormod(((threadIdx.x_1*42) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 1), 27)) && (floormod(((threadIdx.x_1*42) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 1), 27)) && (floormod(((threadIdx.x_1*42) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 2), 27)) && (floormod(((threadIdx.x_1*42) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 2), 27)) && (floormod(((threadIdx.x_1*42) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 2), 27)) && (floormod(((threadIdx.x_1*42) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)) && (floormod(((threadIdx.x_1*42) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dty [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)) && (floormod(((threadIdx.x_1*42) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)) && (floormod(((threadIdx.x_1*42) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 4), 27)) && (floormod(((threadIdx.x_1*42) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 4), 27)) && (floormod(((threadIdx.x_1*42) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 4), 27)) && (floormod(((threadIdx.x_1*42) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 5), 27)) && (floormod(((threadIdx.x_1*42) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 5), 27)) && (floormod(((threadIdx.x_1*42) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 5), 27)) && (floormod(((threadIdx.x_1*42) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 18)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)) && (floormod(((threadIdx.x_1*42) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, d [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 19)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)) && (floormod(((threadIdx.x_1*42) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 20)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)) && (floormod(((threadIdx.x_1*42) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 7), 27)) && (floormod(((threadIdx.x_1*42) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 7), 27)) && (floormod(((threadIdx.x_1*42) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 7), 27)) && (floormod(((threadIdx.x_1*42) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 24)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 8), 27)) && (floormod(((threadIdx.x_1*42) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 25)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 8), 27)) && (floormod(((threadIdx.x_1*42) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 26)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 8), 27)) && (floormod(((threadIdx.x_1*42) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 8), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 27)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)) && (floormod(((threadIdx.x_1*42) + 27), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, d [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 28)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)) && (floormod(((threadIdx.x_1*42) + 28), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 29)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)) && (floormod(((threadIdx.x_1*42) + 29), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 9), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 3), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 30)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 10), 27)) && (floormod(((threadIdx.x_1*42) + 30), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 31)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 10), 27)) && (floormod(((threadIdx.x_1*42) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 32)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 10), 27)) && (floormod(((threadIdx.x_1*42) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 10), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 10), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 33)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 11), 27)) && (floormod(((threadIdx.x_1*42) + 33), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 34)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 11), 27)) && (floormod(((threadIdx.x_1*42) + 34), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 35)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 11), 27)) && (floormod(((threadIdx.x_1*42) + 35), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 11), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 11), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 36)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)) && (floormod(((threadIdx.x_1*42) + 36), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 37)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)) && (floormod(((threadIdx.x_1*42) + 37), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 38)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)) && (floormod(((threadIdx.x_1*42) + 38), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 12), 27)*49)) + (floormod((floordiv((threadIdx.x_1*14), 3) + 4), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 39)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 13), 27)) && (floormod(((threadIdx.x_1*42) + 39), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 40)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 13), 27)) && (floormod(((threadIdx.x_1*42) + 40), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 15), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*42) + 41)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*14) + 13), 27)) && (floormod(((threadIdx.x_1*42) + 41), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*14) + 13), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*14) + 13), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8) [...]
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 28), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 84)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 84), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 140)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 140), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 68), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 196), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 252)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 252), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (yy.outer.inner: int32, 0, 7) {
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18))]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 1)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 2)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 3)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 4)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 5)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 6)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 7)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 8)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 9)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 10)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 11)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 12)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 13)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 14)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 15)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 16)]))
- conv2d_nchw_1[yy.outer.inner] = (conv2d_nchw_1[yy.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*162) + (yy.outer.inner*9)) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + 17)]))
- }
- }
+ for (rc.outer.outer: int32, 0, 32) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [784], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 188)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 580)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [128], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9))]
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 189)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 385)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((7 <= floormod(threadIdx.x_1, 49)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 581)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 1)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 190)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 386)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 49)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 582)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 2)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) - 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 195)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 391)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((1 <= floormod(threadIdx.x_1, 7)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 587)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 3)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = data[((rc.outer.outer*784) + threadIdx.x_1)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = data[(((rc.outer.outer*784) + threadIdx.x_1) + 196)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = data[(((rc.outer.outer*784) + threadIdx.x_1) + 392)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = data[(((rc.outer.outer*784) + threadIdx.x_1) + 588)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 4)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 1)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 197)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 393)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((floormod(threadIdx.x_1, 7) < 6), data[(((rc.outer.outer*784) + threadIdx.x_1) + 589)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 5)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 202)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 398)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (1 <= floormod(threadIdx.x_1, 7))), data[(((rc.outer.outer*784) + threadIdx.x_1) + 594)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 6)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 203)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 399)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((floormod(threadIdx.x_1, 49) < 42), data[(((rc.outer.outer*784) + threadIdx.x_1) + 595)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 7)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 204)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 400)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((floormod(threadIdx.x_1, 49) < 42) && (floormod(threadIdx.x_1, 7) < 6)), data[(((rc.outer.outer*784) + threadIdx.x_1) + 596)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 8)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 147)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 294)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 539)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*32) + 31)]))
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*196) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*4) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -715,7 +929,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.311 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.315 ms
</pre></div>
</div>
</div>
@@ -744,33 +958,33 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
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_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
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_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
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=7)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_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=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_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_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+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_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=1)
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=4)
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=7)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_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=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -793,14 +1007,14 @@ 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=28)
+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=196)
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=42)
+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=28)
+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=196)
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", 64)
+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, "unroll_explicit", True)
CUDA source code:
@@ -818,184 +1032,385 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[288];
+extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[784];
+ __shared__ float kernel_shared[128];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[(((int)threadIdx.x) * 42)] = (((((3 <= ((((int)threadIdx.x) * 14) % 27)) && (((((int)threadIdx.x) * 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 14) / 27) * 49)) + ((((((int)threadIdx.x) * 14) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 1)] = (((((3 <= ((((int)threadIdx.x) * 14) % 27)) && ((((((int)threadIdx.x) * 42) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 14) / 27) * 49)) + ((((((int)threadIdx.x) * 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 2)] = (((((3 <= ((((int)threadIdx.x) * 14) % 27)) && ((((((int)threadIdx.x) * 42) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 14) / 27) * 49)) + ((((((int)threadIdx.x) * 14) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 3)] = (((((3 <= (((((int)threadIdx.x) * 14) + 1) % 27)) && ((((((int)threadIdx.x) * 42) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 4)] = (((((3 <= (((((int)threadIdx.x) * 14) + 1) % 27)) && ((((((int)threadIdx.x) * 42) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 5)] = (((((3 <= (((((int)threadIdx.x) * 14) + 1) % 27)) && ((((((int)threadIdx.x) * 42) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 6)] = (((((3 <= (((((int)threadIdx.x) * 14) + 2) % 27)) && ((((((int)threadIdx.x) * 42) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 7)] = (((((3 <= (((((int)threadIdx.x) * 14) + 2) % 27)) && ((((((int)threadIdx.x) * 42) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 8)] = (((((3 <= (((((int)threadIdx.x) * 14) + 2) % 27)) && ((((((int)threadIdx.x) * 42) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 42) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 42) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 42) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 12)] = (((((3 <= (((((int)threadIdx.x) * 14) + 4) % 27)) && ((((((int)threadIdx.x) * 42) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 13)] = (((((3 <= (((((int)threadIdx.x) * 14) + 4) % 27)) && ((((((int)threadIdx.x) * 42) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 14)] = (((((3 <= (((((int)threadIdx.x) * 14) + 4) % 27)) && ((((((int)threadIdx.x) * 42) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 15)] = (((((3 <= (((((int)threadIdx.x) * 14) + 5) % 27)) && ((((((int)threadIdx.x) * 42) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 16)] = (((((3 <= (((((int)threadIdx.x) * 14) + 5) % 27)) && ((((((int)threadIdx.x) * 42) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 16) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 17)] = (((((3 <= (((((int)threadIdx.x) * 14) + 5) % 27)) && ((((((int)threadIdx.x) * 42) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 18)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 42) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 19)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 42) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 20)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 42) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 21)] = (((((3 <= (((((int)threadIdx.x) * 14) + 7) % 27)) && ((((((int)threadIdx.x) * 42) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 22)] = (((((3 <= (((((int)threadIdx.x) * 14) + 7) % 27)) && ((((((int)threadIdx.x) * 42) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 188)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((7 <= (((int)threadIdx.x) % 49)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 580)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9))];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 23)] = (((((3 <= (((((int)threadIdx.x) * 14) + 7) % 27)) && ((((((int)threadIdx.x) * 42) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 24)] = (((((3 <= (((((int)threadIdx.x) * 14) + 8) % 27)) && ((((((int)threadIdx.x) * 42) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 25)] = (((((3 <= (((((int)threadIdx.x) * 14) + 8) % 27)) && ((((((int)threadIdx.x) * 42) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 26)] = (((((3 <= (((((int)threadIdx.x) * 14) + 8) % 27)) && ((((((int)threadIdx.x) * 42) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 8) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 27)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 42) + 27) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 28)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 42) + 28) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 29)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 3) % 9)) && ((((((int)threadIdx.x) * 42) + 29) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 9) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 30)] = (((((3 <= (((((int)threadIdx.x) * 14) + 10) % 27)) && ((((((int)threadIdx.x) * 42) + 30) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 31)] = (((((3 <= (((((int)threadIdx.x) * 14) + 10) % 27)) && ((((((int)threadIdx.x) * 42) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 32)] = (((((3 <= (((((int)threadIdx.x) * 14) + 10) % 27)) && ((((((int)threadIdx.x) * 42) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 10) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 10) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 33)] = (((((3 <= (((((int)threadIdx.x) * 14) + 11) % 27)) && ((((((int)threadIdx.x) * 42) + 33) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 34)] = (((((3 <= (((((int)threadIdx.x) * 14) + 11) % 27)) && ((((((int)threadIdx.x) * 42) + 34) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 35)] = (((((3 <= (((((int)threadIdx.x) * 14) + 11) % 27)) && ((((((int)threadIdx.x) * 42) + 35) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 11) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 11) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 36)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 42) + 36) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 4) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 189)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 385)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((7 <= (((int)threadIdx.x) % 49)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 581)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 1)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 37)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 42) + 37) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 190)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 386)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((7 <= (((int)threadIdx.x) % 49)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 582)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 2)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 38)] = (((((1 <= ((((((int)threadIdx.x) * 14) / 3) + 4) % 9)) && ((((((int)threadIdx.x) * 42) + 38) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 12) / 27) * 49)) + (((((((int)threadIdx.x) * 14) / 3) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 195)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 391)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((1 <= (((int)threadIdx.x) % 7)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 587)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 3)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 39)] = (((((3 <= (((((int)threadIdx.x) * 14) + 13) % 27)) && ((((((int)threadIdx.x) * 42) + 39) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = data[((rc_outer_outer * 784) + ((int)threadIdx.x))];
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 196)];
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 392)];
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 588)];
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 4)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 40)] = (((((3 <= (((((int)threadIdx.x) * 14) + 13) % 27)) && ((((((int)threadIdx.x) * 42) + 40) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 1)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 197)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 393)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((int)threadIdx.x) % 7) < 6) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 589)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 5)];
}
- if (((int)threadIdx.x) < 15) {
- pad_temp_shared[((((int)threadIdx.x) * 42) + 41)] = (((((3 <= (((((int)threadIdx.x) * 14) + 13) % 27)) && ((((((int)threadIdx.x) * 42) + 41) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 14) + 13) / 27) * 49)) + (((((((int)threadIdx.x) * 14) + 13) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 202)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 398)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((int)threadIdx.x) % 49) < 42) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 594)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 6)];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 18432) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 28)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 28) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 84)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 84) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 140)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 140) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 68) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 52) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 252)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 252) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36)];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 203)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 399)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((int)threadIdx.x) % 49) < 42) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 595)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 7)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18))]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 1)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 2)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 3)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 4)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 5)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 6)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 7)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 8)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 9)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 10)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 11)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 12)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 13)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 14)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 15)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 16)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 162) + (yy_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + 17)]));
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 204)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 400)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((int)threadIdx.x) % 49) < 42) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((rc_outer_outer * 784) + ((int)threadIdx.x)) + 596)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 8)];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 98)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 147)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 294)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 490)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 539)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 588)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 686)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 735)] * kernel_shared[(((((int)threadIdx.x) / 49) * 32) + 31)]));
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 196) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 4) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1032,7 +1447,7 @@ 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 32.501 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 50.626 seconds)</p>
<div class="sphx-glr-footer 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 sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 11d277af6..1a279807e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ 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)
- 9.8249 9.8201 9.8735 9.7811 0.0379
+ 9.8018 9.7943 9.8533 9.7577 0.0394
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index c0ecfd002..571324583 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ 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)
- 752.2819 751.9914 752.8943 751.9599 0.4333
+ 781.6611 781.5751 782.7018 780.7064 0.8169
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ 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 20.510 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.319 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python 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 683dc3c94..305e089d0 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,80 +620,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
for (i.outer.inner: int32, 0, 2) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[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 (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [128], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder[((((i0.outer*2048) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
- }
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_2: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
+ compute[ramp(cse_var_2, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -731,7 +681,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.699 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.312 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 1d25e6fdf..a52309720 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:43.710</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.485</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:43.677</p></td>
+<td><p>00:44.450</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.019</p></td>
+<td><p>00:00.022</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
@@ -343,7 +343,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
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 4dbf8f154..72b6a5362 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1164,8 +1164,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 96.72/96.72 result: MeasureResult(costs=(0.002393513375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7802348136901855, timestamp=1656432764.1831858) [('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: 0.00/96.72 result: Traceback (most recent call last):
+No: 6 GFLOPS: 92.66/92.66 result: MeasureResult(costs=(0.0024983592916666664,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8174035549163818, timestamp=1656435149.146044) [('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: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1288,7 +1288,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1411,7 +1411,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1534,7 +1534,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/92.66 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
@@ -1552,7 +1552,7 @@ No: 10 GFLOPS: 0.00/96.72 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1675,7 +1675,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1798,7 +1798,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1921,7 +1921,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2044,7 +2044,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2167,7 +2167,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2290,7 +2290,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2413,7 +2413,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2536,7 +2536,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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: 0.00/96.72 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/92.66 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2624,7 +2624,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f348964bfa2
+ 12: 0x00007f78e1d6cfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2689,7 +2689,7 @@ 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: 143.91/143.91 result: MeasureResult(costs=(0.0016086114285714284,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.156287431716919, timestamp=1656432790.550082) [('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: 144.91/144.91 result: MeasureResult(costs=(0.00159756869,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.479034185409546, timestamp=1656435175.3001082) [('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,
@@ -2730,7 +2730,7 @@ and measure running time.</p>
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
Finish loading 20 records
-Time cost of this operator: 0.002076
+Time cost of this operator: 0.002015
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 970f18631..06ccea2ed 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.1 98.777 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.982 0.935 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.919 0.288 (1, 1, 10, 10, 3) 1 1
-Total_time - 319.002 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.4 98.712 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.169 1.001 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 0.286 (1, 1, 10, 10, 3) 1 1
+Total_time - 316.475 - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ Total_time -
########## 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 319.8 99.104 (1, 3, 10, 10, 2) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.08 0.644 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.813 0.252 (1, 3, 10, 10, 1) 1 1
-Total_time - 322.692 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 193.3 98.591 (1, 1, 10, 10, 6) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.948 0.994 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.814 0.415 (1, 3, 10, 10, 1) 1 1
+Total_time - 196.062 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 5917e678f..74d067c4e 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpscudv4x_/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpe4lzkuo7/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpscudv4x_/images/target contains 8144 images
-/tmp/tmpscudv4x_/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpe4lzkuo7/images/target contains 8144 images
+/tmp/tmpe4lzkuo7/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2340 - accuracy: 0.9209 - val_loss: 0.1365 - val_accuracy: 0.9600
+328/328 - 56s - loss: 0.2139 - accuracy: 0.9265 - val_loss: 0.1406 - val_accuracy: 0.9585
Epoch 2/3
-328/328 - 52s - loss: 0.1023 - accuracy: 0.9611 - val_loss: 0.1142 - val_accuracy: 0.9637
+328/328 - 53s - loss: 0.0946 - accuracy: 0.9640 - val_loss: 0.1143 - val_accuracy: 0.9622
Epoch 3/3
-328/328 - 52s - loss: 0.0727 - accuracy: 0.9736 - val_loss: 0.1176 - val_accuracy: 0.9615
+328/328 - 53s - loss: 0.0644 - accuracy: 0.9750 - val_loss: 0.1077 - val_accuracy: 0.9615
-<keras.callbacks.History object at 0x7fa684136d50>
+<keras.callbacks.History object at 0x7f70e1793910>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 9 minutes 4.481 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 59.379 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 54d4badde..e6201a481 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>09:51.623</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>08:49.433</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>09:04.481</p></td>
+<td><p>07:59.379</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:43.578</p></td>
+<td><p>00:46.244</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:03.563</p></td>
+<td><p>00:03.810</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
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 80543a89c..d6c1a4a77 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:11.592</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:10.272</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:10.027</p></td>
+<td><p>00:08.647</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:01.559</p></td>
+<td><p>00:01.619</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 000dcf252..4f18385af 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -515,7 +515,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fa5e7d8af80>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f7062f893b0>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
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 cca444451..7cfb4fd14 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:04.124</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.314</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,35 +331,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:01.934</p></td>
+<td><p>00:01.973</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.956</p></td>
+<td><p>00:01.061</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.537</p></td>
+<td><p>00:00.554</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.523</p></td>
+<td><p>00:00.539</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.099</p></td>
+<td><p>00:00.106</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.035</p></td>
+<td><p>00:00.038</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.027</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.013</p></td>
+<td><p>00:00.014</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 35b0c6419..5da52095b 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -571,7 +571,7 @@ 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/tmpxp2lxik8/input0.cc'\nsource_filename = \"/tmp/tmpxp2lxik8/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/tmpxx53k_i6/input0.cc'\nsource_filename = \"/tmp/tmpxx53k_i6/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 4768dd785..89c0e34e5 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1597,7 +1597,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<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>
@@ -1881,7 +1881,7 @@ Candidates:
<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">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 8fba1ca4b..763b4494d 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/bd49b0846/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 76e358990..bb4e955cb 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/bd49b0846/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 c0ea139a6..9d5e91a76 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/bd49b0846/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 7c84c564b..be2fbbb18 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/bd49b0846/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 251c50bbf..4818adc1f 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/bd49b0846/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 55faf74d8..8bd930454 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/bd49b0846/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 0ada0ab5e..9b37deab0 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/bd49b0846/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 3fe803fc4..6e1d05ce3 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/bd49b0846/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 a63bb22a7..52e4dc4aa 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/bd49b0846/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 a2ebaf2d3..ae3f7a271 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/bd49b0846/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 0be2d0299..2f68319f2 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/bd49b0846/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 051b22515..fc0d15dec 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/bd49b0846/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 1a0be8e40..4b3b98168 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/bd49b0846/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 ed7167bc7..edb7325c4 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/bd49b0846/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 a353ec68c..504c3e79f 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/bd49b0846/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 b8fd42006..198cf802b 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/bd49b0846/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 02c2214f9..56e081a8e 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/bd49b0846/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 6af6a6606..b11f9650b 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/bd49b0846/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 5f31a0e2e..d461e5a77 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/bd49b0846/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 286950b82..ffef31a9c 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/bd49b0846/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 f6f575f33..494534d38 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/bd49b0846/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 8b26f14af..9916df706 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/bd49b0846/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 36e9acba3..e54743cdb 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/bd49b0846/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 550ef514a..e2bd37dfa 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/bd49b0846/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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/bd49b0846/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b733aa3ec/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 c2687b886..fc631f2e9 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 197d5364d..0fb889c2a 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:20.988</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:22.494</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:20.982</p></td>
+<td><p>00:22.488</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index bad36a44e..f14a2f793 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
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 22.92s!
+resnet18_v1 inference graph built in 24.72s!
</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 40d97f9b9..fe9c59e57 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.82s!
+yolov3-tiny inference graph built in 17.09s!
</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 dcde46146..ac34869a3 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>01:30.864</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:34.796</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:47.752</p></td>
+<td><p>00:49.419</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:43.112</p></td>
+<td><p>00:45.377</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 944a37144..022faba48 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:03.229</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.331</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:02.816</p></td>
+<td><p>00:02.911</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.413</p></td>
+<td><p>00:00.420</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index d449cb103..dcfe01cc1 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:00.756</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.778</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.407</p></td>
+<td><p>00:00.406</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.350</p></td>
+<td><p>00:00.372</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index ff8e62388..543ca1718 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -561,7 +561,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.361 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 96.466 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 6484aca85..30272b592 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -660,16 +660,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 9.54/9.54 result: MeasureResult(costs=(0.0281370082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5838139057159424, timestamp=1656431544.0756063) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.91/9.54 result: MeasureResult(costs=(0.09230103840000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6288020610809326, timestamp=1656431546.2400708) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.75/11.75 result: MeasureResult(costs=(0.022836872799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5916013717651367, timestamp=1656431546.8131716) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.46/11.75 result: MeasureResult(costs=(0.1844247434,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0677573680877686, timestamp=1656431550.451093) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.58/11.75 result: MeasureResult(costs=(0.0749565606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3438076972961426, timestamp=1656431551.9296255) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.82/11.75 result: MeasureResult(costs=(0.1473566616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.479562520980835, timestamp=1656431554.97117) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.86/11.75 result: MeasureResult(costs=(0.3121382228,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.116043329238892, timestamp=1656431560.1299756) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.19/11.75 result: MeasureResult(costs=(0.026338152200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5656037330627441, timestamp=1656431560.715064) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.54/11.75 result: MeasureResult(costs=(0.17431820920000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.891237735748291, timestamp=1656431563.7274027) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.67/11.75 result: MeasureResult(costs=(0.10049530200000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7167799472808838, timestamp=1656431565.5037563) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.71/9.71 result: MeasureResult(costs=(0.027646069999999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5867083072662354, timestamp=1656433966.7181191) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.79/9.71 result: MeasureResult(costs=(0.0961177002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6903934478759766, timestamp=1656433968.4228745) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.58/11.58 result: MeasureResult(costs=(0.0231874504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5625529289245605, timestamp=1656433969.5204566) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.65/11.58 result: MeasureResult(costs=(0.1624127696,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7210912704467773, timestamp=1656433972.853541) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.60/11.58 result: MeasureResult(costs=(0.07464471180000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3431448936462402, timestamp=1656433974.3254597) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.59/11.58 result: MeasureResult(costs=(0.16834135060000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8646767139434814, timestamp=1656433977.2320302) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.83/11.58 result: MeasureResult(costs=(0.3225357506,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.3336381912231445, timestamp=1656433983.1740465) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 9.59/11.58 result: MeasureResult(costs=(0.027990559200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6055922508239746, timestamp=1656433983.787655) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.56/11.58 result: MeasureResult(costs=(0.1720130958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.860116720199585, timestamp=1656433986.7689433) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.64/11.58 result: MeasureResult(costs=(0.10176397159999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.74306321144104, timestamp=1656433988.5698962) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 428ee7871..46b82765b 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -542,7 +542,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 495.8506218799994, 'median': 495.5960244999005, 'std': 0.9961609385082597}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 505.915253750004, 'median': 505.9168230500063, 'std': 0.8558069739254331}
</pre></div>
</div>
</div>
@@ -697,179 +697,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 5.81 s
-[Task 1/25] Current/Best: 6.15/ 17.42 GFLOPS | Progress: (8/20) | 9.28 s
-[Task 1/25] Current/Best: 11.55/ 22.64 GFLOPS | Progress: (12/20) | 11.70 s
-[Task 1/25] Current/Best: 16.69/ 22.71 GFLOPS | Progress: (16/20) | 13.39 s
-[Task 1/25] Current/Best: 11.58/ 23.89 GFLOPS | Progress: (20/20) | 15.14 s Done.
+[Task 1/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (4/20) | 6.57 s
+[Task 1/25] Current/Best: 6.15/ 17.31 GFLOPS | Progress: (8/20) | 9.66 s
+[Task 1/25] Current/Best: 11.45/ 22.40 GFLOPS | Progress: (12/20) | 12.27 s
+[Task 1/25] Current/Best: 16.49/ 22.42 GFLOPS | Progress: (16/20) | 14.02 s
+[Task 1/25] Current/Best: 11.54/ 23.54 GFLOPS | Progress: (20/20) | 15.82 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.21/ 12.95 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 2/25] Current/Best: 14.12/ 18.58 GFLOPS | Progress: (8/20) | 4.97 s
-[Task 2/25] Current/Best: 20.77/ 20.77 GFLOPS | Progress: (12/20) | 6.29 s
-[Task 2/25] Current/Best: 12.44/ 20.77 GFLOPS | Progress: (16/20) | 7.55 s
-[Task 2/25] Current/Best: 19.90/ 20.77 GFLOPS | Progress: (20/20) | 9.11 s Done.
+[Task 2/25] Current/Best: 11.89/ 12.76 GFLOPS | Progress: (4/20) | 4.13 s
+[Task 2/25] Current/Best: 14.04/ 17.26 GFLOPS | Progress: (8/20) | 5.49 s
+[Task 2/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 6.86 s
+[Task 2/25] Current/Best: 12.74/ 20.66 GFLOPS | Progress: (16/20) | 8.20 s
+[Task 2/25] Current/Best: 19.55/ 20.66 GFLOPS | Progress: (20/20) | 9.83 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/ 10.57 GFLOPS | Progress: (4/20) | 5.89 s
-[Task 3/25] Current/Best: 15.54/ 16.84 GFLOPS | Progress: (8/20) | 7.84 s
-[Task 3/25] Current/Best: 14.87/ 16.84 GFLOPS | Progress: (12/20) | 9.60 s
-[Task 3/25] Current/Best: 7.21/ 23.60 GFLOPS | Progress: (16/20) | 11.52 s
-[Task 3/25] Current/Best: 12.54/ 23.60 GFLOPS | Progress: (20/20) | 16.08 s Done.
+[Task 3/25] Current/Best: 1.62/ 10.53 GFLOPS | Progress: (4/20) | 5.96 s
+[Task 3/25] Current/Best: 15.50/ 16.85 GFLOPS | Progress: (8/20) | 7.92 s
+[Task 3/25] Current/Best: 14.81/ 16.85 GFLOPS | Progress: (12/20) | 9.67 s
+[Task 3/25] Current/Best: 7.20/ 23.66 GFLOPS | Progress: (16/20) | 11.61 s
+[Task 3/25] Current/Best: 12.54/ 23.66 GFLOPS | Progress: (20/20) | 16.26 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.54/ 20.44 GFLOPS | Progress: (4/20) | 2.40 s
-[Task 4/25] Current/Best: 6.87/ 20.44 GFLOPS | Progress: (8/20) | 6.76 s
-[Task 4/25] Current/Best: 22.14/ 22.14 GFLOPS | Progress: (12/20) | 11.33 s
-[Task 4/25] Current/Best: 16.38/ 22.14 GFLOPS | Progress: (16/20) | 13.58 s
-[Task 4/25] Current/Best: 13.30/ 22.14 GFLOPS | Progress: (20/20) | 15.56 s Done.
+[Task 4/25] Current/Best: 9.50/ 20.16 GFLOPS | Progress: (4/20) | 2.52 s
+[Task 4/25] Current/Best: 6.85/ 20.16 GFLOPS | Progress: (8/20) | 7.06 s
+[Task 4/25] Current/Best: 21.59/ 21.59 GFLOPS | Progress: (12/20) | 11.84 s
+[Task 4/25] Current/Best: 17.22/ 21.59 GFLOPS | Progress: (16/20) | 14.15 s
+[Task 4/25] Current/Best: 13.03/ 21.59 GFLOPS | Progress: (20/20) | 16.10 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.53/ 10.31 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 5/25] Current/Best: 11.71/ 12.95 GFLOPS | Progress: (8/20) | 4.66 s
-[Task 5/25] Current/Best: 9.85/ 18.03 GFLOPS | Progress: (12/20) | 7.79 s
-[Task 5/25] Current/Best: 11.81/ 22.60 GFLOPS | Progress: (16/20) | 9.21 s
-[Task 5/25] Current/Best: 11.85/ 22.60 GFLOPS | Progress: (20/20) | 11.09 s Done.
+[Task 5/25] Current/Best: 9.03/ 10.02 GFLOPS | Progress: (4/20) | 2.70 s
+[Task 5/25] Current/Best: 11.34/ 12.71 GFLOPS | Progress: (8/20) | 4.83 s
+[Task 5/25] Current/Best: 9.44/ 17.04 GFLOPS | Progress: (12/20) | 7.89 s
+[Task 5/25] Current/Best: 11.21/ 22.32 GFLOPS | Progress: (16/20) | 9.35 s
+[Task 5/25] Current/Best: 10.48/ 22.32 GFLOPS | Progress: (20/20) | 11.27 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.22/ 20.75 GFLOPS | Progress: (4/20) | 3.98 s
-[Task 6/25] Current/Best: 18.88/ 20.75 GFLOPS | Progress: (8/20) | 5.73 s
-[Task 6/25] Current/Best: 13.23/ 20.75 GFLOPS | Progress: (12/20) | 7.65 s
-[Task 6/25] Current/Best: 19.93/ 20.75 GFLOPS | Progress: (16/20) | 9.89 s
-[Task 6/25] Current/Best: 3.73/ 20.75 GFLOPS | Progress: (20/20) | 12.41 s Done.
+[Task 6/25] Current/Best: 12.24/ 20.49 GFLOPS | Progress: (4/20) | 4.14 s
+[Task 6/25] Current/Best: 18.66/ 20.49 GFLOPS | Progress: (8/20) | 5.93 s
+[Task 6/25] Current/Best: 11.77/ 20.49 GFLOPS | Progress: (12/20) | 7.91 s
+[Task 6/25] Current/Best: 19.66/ 20.49 GFLOPS | Progress: (16/20) | 10.19 s
+[Task 6/25] Current/Best: 3.67/ 20.49 GFLOPS | Progress: (20/20) | 12.74 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.22/ 12.94 GFLOPS | Progress: (4/20) | 3.55 s
-[Task 7/25] Current/Best: 20.09/ 20.95 GFLOPS | Progress: (8/20) | 5.07 s
-[Task 7/25] Current/Best: 15.91/ 20.95 GFLOPS | Progress: (12/20) | 6.97 s
-[Task 7/25] Current/Best: 12.20/ 20.95 GFLOPS | Progress: (16/20) | 9.02 s
-[Task 7/25] Current/Best: 6.37/ 21.70 GFLOPS | Progress: (20/20) | 11.48 s Done.
+[Task 7/25] Current/Best: 10.99/ 12.11 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 7/25] Current/Best: 19.70/ 20.88 GFLOPS | Progress: (8/20) | 5.26 s
+[Task 7/25] Current/Best: 15.64/ 20.88 GFLOPS | Progress: (12/20) | 7.20 s
+[Task 7/25] Current/Best: 12.20/ 20.88 GFLOPS | Progress: (16/20) | 9.30 s
+[Task 7/25] Current/Best: 6.43/ 21.72 GFLOPS | Progress: (20/20) | 11.77 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.08/ 14.24 GFLOPS | Progress: (4/20) | 2.91 s
-[Task 8/25] Current/Best: 9.41/ 14.24 GFLOPS | Progress: (8/20) | 7.67 s
-[Task 8/25] Current/Best: 12.83/ 14.24 GFLOPS | Progress: (12/20) | 13.85 s
-[Task 8/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (16/20) | 15.93 s
-[Task 8/25] Current/Best: 19.93/ 19.93 GFLOPS | Progress: (20/20) | 22.44 s Done.
+[Task 8/25] Current/Best: 9.95/ 14.31 GFLOPS | Progress: (4/20) | 3.01 s
+[Task 8/25] Current/Best: 9.59/ 14.31 GFLOPS | Progress: (8/20) | 7.98 s
+[Task 8/25] Current/Best: 12.80/ 14.31 GFLOPS | Progress: (12/20) | 14.42 s
+[Task 8/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (16/20) | 16.54 s
+[Task 8/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (20/20) | 23.29 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.24/ 15.77 GFLOPS | Progress: (4/20) | 11.96 s
-[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.72 s
-[Task 9/25] Current/Best: 8.21/ 23.41 GFLOPS | Progress: (12/20) | 16.09 s
-[Task 9/25] Current/Best: 17.94/ 23.41 GFLOPS | Progress: (16/20) | 18.76 s
-[Task 9/25] Current/Best: 8.98/ 23.41 GFLOPS | Progress: (20/20) | 26.46 s
+[Task 9/25] Current/Best: 14.19/ 15.18 GFLOPS | Progress: (4/20) | 12.05 s
+[Task 9/25] Current/Best: 22.48/ 22.48 GFLOPS | Progress: (8/20) | 13.91 s
+[Task 9/25] Current/Best: 8.21/ 22.48 GFLOPS | Progress: (12/20) | 16.32 s
+[Task 9/25] Current/Best: 17.72/ 22.48 GFLOPS | Progress: (16/20) | 19.06 s
+[Task 9/25] Current/Best: 8.89/ 22.48 GFLOPS | Progress: (20/20) | 27.25 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.51/ 18.51 GFLOPS | Progress: (4/20) | 2.59 s
-[Task 10/25] Current/Best: 15.57/ 18.51 GFLOPS | Progress: (8/20) | 4.17 s
-[Task 10/25] Current/Best: 12.60/ 18.94 GFLOPS | Progress: (12/20) | 5.71 s
-[Task 10/25] Current/Best: 19.07/ 20.33 GFLOPS | Progress: (16/20) | 6.82 s
-[Task 10/25] Current/Best: 8.87/ 20.33 GFLOPS | Progress: (20/20) | 8.35 s Done.
+[Task 10/25] Current/Best: 18.48/ 18.48 GFLOPS | Progress: (4/20) | 2.70 s
+[Task 10/25] Current/Best: 15.33/ 18.48 GFLOPS | Progress: (8/20) | 4.33 s
+[Task 10/25] Current/Best: 12.18/ 19.07 GFLOPS | Progress: (12/20) | 5.89 s
+[Task 10/25] Current/Best: 18.85/ 20.10 GFLOPS | Progress: (16/20) | 7.04 s
+[Task 10/25] Current/Best: 8.92/ 20.10 GFLOPS | Progress: (20/20) | 8.62 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.31/ 18.10 GFLOPS | Progress: (4/20) | 3.35 s
-[Task 11/25] Current/Best: 16.84/ 18.10 GFLOPS | Progress: (8/20) | 6.09 s
-[Task 11/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (12/20) | 8.15 s
-[Task 11/25] Current/Best: 13.39/ 21.14 GFLOPS | Progress: (16/20) | 10.88 s
-[Task 11/25] Current/Best: 19.41/ 21.14 GFLOPS | Progress: (20/20) | 12.89 s Done.
+[Task 11/25] Current/Best: 12.08/ 17.78 GFLOPS | Progress: (4/20) | 3.46 s
+[Task 11/25] Current/Best: 16.10/ 17.78 GFLOPS | Progress: (8/20) | 6.28 s
+[Task 11/25] Current/Best: 17.87/ 17.87 GFLOPS | Progress: (12/20) | 8.42 s
+[Task 11/25] Current/Best: 13.41/ 21.13 GFLOPS | Progress: (16/20) | 11.43 s
+[Task 11/25] Current/Best: 19.10/ 21.46 GFLOPS | Progress: (20/20) | 13.50 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.80/ 18.23 GFLOPS | Progress: (4/20) | 5.43 s
-[Task 12/25] Current/Best: 5.20/ 18.23 GFLOPS | Progress: (8/20) | 9.16 s
-[Task 12/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (12/20) | 11.18 s
-[Task 12/25] Current/Best: 15.09/ 18.97 GFLOPS | Progress: (16/20) | 13.96 s
-[Task 12/25] Current/Best: 15.15/ 18.97 GFLOPS | Progress: (20/20) | 15.88 s Done.
+[Task 12/25] Current/Best: 7.71/ 18.21 GFLOPS | Progress: (4/20) | 5.60 s
+[Task 12/25] Current/Best: 5.20/ 18.21 GFLOPS | Progress: (8/20) | 9.43 s
+[Task 12/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 11.45 s
+[Task 12/25] Current/Best: 12.44/ 19.05 GFLOPS | Progress: (16/20) | 14.34 s
+[Task 12/25] Current/Best: 15.17/ 19.05 GFLOPS | Progress: (20/20) | 16.26 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.72/ 17.33 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 13/25] Current/Best: 16.02/ 20.73 GFLOPS | Progress: (8/20) | 6.11 s
-[Task 13/25] Current/Best: 19.35/ 21.42 GFLOPS | Progress: (12/20) | 9.00 s
-[Task 13/25] Current/Best: 12.22/ 21.42 GFLOPS | Progress: (16/20) | 12.40 s
-[Task 13/25] Current/Best: 18.78/ 21.42 GFLOPS | Progress: (20/20) | 14.61 s Done.
+[Task 13/25] Current/Best: 8.84/ 17.27 GFLOPS | Progress: (4/20) | 3.80 s
+[Task 13/25] Current/Best: 15.29/ 20.66 GFLOPS | Progress: (8/20) | 6.32 s
+[Task 13/25] Current/Best: 19.36/ 20.90 GFLOPS | Progress: (12/20) | 9.30 s
+[Task 13/25] Current/Best: 12.17/ 20.90 GFLOPS | Progress: (16/20) | 12.75 s
+[Task 13/25] Current/Best: 18.17/ 20.90 GFLOPS | Progress: (20/20) | 15.04 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.54/ 13.54 GFLOPS | Progress: (4/20) | 3.34 s
-[Task 14/25] Current/Best: 6.07/ 13.54 GFLOPS | Progress: (8/20) | 5.50 s
-[Task 14/25] Current/Best: 20.30/ 20.30 GFLOPS | Progress: (12/20) | 8.07 s
-[Task 14/25] Current/Best: 16.56/ 20.30 GFLOPS | Progress: (16/20) | 9.71 s Done.
+[Task 14/25] Current/Best: 13.27/ 13.27 GFLOPS | Progress: (4/20) | 3.40 s
+[Task 14/25] Current/Best: 6.11/ 13.27 GFLOPS | Progress: (8/20) | 5.60 s
+[Task 14/25] Current/Best: 19.49/ 19.49 GFLOPS | Progress: (12/20) | 8.21 s
+[Task 14/25] Current/Best: 16.17/ 19.49 GFLOPS | Progress: (16/20) | 9.88 s Done.
-[Task 14/25] Current/Best: 17.27/ 20.30 GFLOPS | Progress: (20/20) | 11.46 s
+[Task 14/25] Current/Best: 17.13/ 19.49 GFLOPS | Progress: (20/20) | 11.66 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.14/ 17.61 GFLOPS | Progress: (4/20) | 2.75 s
-[Task 15/25] Current/Best: 14.35/ 18.00 GFLOPS | Progress: (8/20) | 4.04 s
-[Task 15/25] Current/Best: 10.40/ 22.28 GFLOPS | Progress: (12/20) | 6.10 s
-[Task 15/25] Current/Best: 20.43/ 22.28 GFLOPS | Progress: (16/20) | 9.27 s
-[Task 15/25] Current/Best: 9.63/ 22.28 GFLOPS | Progress: (20/20) | 10.30 s
+[Task 15/25] Current/Best: 16.04/ 17.42 GFLOPS | Progress: (4/20) | 2.85 s
+[Task 15/25] Current/Best: 14.32/ 17.87 GFLOPS | Progress: (8/20) | 4.23 s
+[Task 15/25] Current/Best: 10.32/ 20.99 GFLOPS | Progress: (12/20) | 6.39 s
+[Task 15/25] Current/Best: 20.07/ 20.99 GFLOPS | Progress: (16/20) | 9.68 s
+[Task 15/25] Current/Best: 9.56/ 20.99 GFLOPS | Progress: (20/20) | 10.73 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (4/20) | 2.95 s
-[Task 16/25] Current/Best: 3.04/ 20.62 GFLOPS | Progress: (8/20) | 4.56 s
-[Task 16/25] Current/Best: 19.25/ 20.62 GFLOPS | Progress: (12/20) | 5.78 s
-[Task 16/25] Current/Best: 17.68/ 20.62 GFLOPS | Progress: (16/20) | 7.12 s
-[Task 16/25] Current/Best: 10.08/ 20.62 GFLOPS | Progress: (20/20) | 9.19 s Done.
+[Task 16/25] Current/Best: 20.17/ 20.17 GFLOPS | Progress: (4/20) | 3.07 s
+[Task 16/25] Current/Best: 3.03/ 20.17 GFLOPS | Progress: (8/20) | 4.71 s
+[Task 16/25] Current/Best: 18.83/ 20.17 GFLOPS | Progress: (12/20) | 5.96 s
+[Task 16/25] Current/Best: 17.65/ 20.17 GFLOPS | Progress: (16/20) | 7.33 s
+[Task 16/25] Current/Best: 9.80/ 21.65 GFLOPS | Progress: (20/20) | 9.46 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.88/ 18.77 GFLOPS | Progress: (4/20) | 4.72 s
-[Task 17/25] Current/Best: 14.44/ 23.02 GFLOPS | Progress: (8/20) | 7.60 s
-[Task 17/25] Current/Best: 16.50/ 23.02 GFLOPS | Progress: (12/20) | 9.64 s
-[Task 17/25] Current/Best: 16.81/ 23.02 GFLOPS | Progress: (16/20) | 11.79 s
-[Task 17/25] Current/Best: 10.03/ 23.02 GFLOPS | Progress: (20/20) | 13.92 s Done.
+[Task 17/25] Current/Best: 14.08/ 18.85 GFLOPS | Progress: (4/20) | 4.84 s
+[Task 17/25] Current/Best: 14.37/ 22.73 GFLOPS | Progress: (8/20) | 7.68 s
+[Task 17/25] Current/Best: 16.80/ 22.73 GFLOPS | Progress: (12/20) | 9.77 s
+[Task 17/25] Current/Best: 16.72/ 22.73 GFLOPS | Progress: (16/20) | 11.95 s
+[Task 17/25] Current/Best: 10.02/ 22.73 GFLOPS | Progress: (20/20) | 14.12 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.22/ 17.40 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 18/25] Current/Best: 10.57/ 19.88 GFLOPS | Progress: (8/20) | 7.16 s
-[Task 18/25] Current/Best: 18.89/ 19.88 GFLOPS | Progress: (12/20) | 9.11 s
-[Task 18/25] Current/Best: 9.86/ 19.88 GFLOPS | Progress: (16/20) | 12.73 s
-[Task 18/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (20/20) | 14.26 s Done.
+[Task 18/25] Current/Best: 11.21/ 17.92 GFLOPS | Progress: (4/20) | 3.86 s
+[Task 18/25] Current/Best: 10.55/ 19.57 GFLOPS | Progress: (8/20) | 7.46 s
+[Task 18/25] Current/Best: 19.21/ 19.57 GFLOPS | Progress: (12/20) | 9.41 s
+[Task 18/25] Current/Best: 9.85/ 19.57 GFLOPS | Progress: (16/20) | 13.17 s
+[Task 18/25] Current/Best: 20.70/ 20.70 GFLOPS | Progress: (20/20) | 14.72 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.18/ 20.18 GFLOPS | Progress: (4/20) | 6.08 s
-[Task 19/25] Current/Best: 2.61/ 20.18 GFLOPS | Progress: (8/20) | 9.33 s
-[Task 19/25] Current/Best: 19.45/ 20.47 GFLOPS | Progress: (12/20) | 12.11 s
-[Task 19/25] Current/Best: 14.80/ 21.32 GFLOPS | Progress: (16/20) | 14.91 s
-[Task 19/25] Current/Best: 2.70/ 23.05 GFLOPS | Progress: (20/20) | 17.69 s Done.
+[Task 19/25] Current/Best: 5.37/ 20.02 GFLOPS | Progress: (4/20) | 6.52 s
+[Task 19/25] Current/Best: 2.60/ 20.02 GFLOPS | Progress: (8/20) | 9.84 s
+[Task 19/25] Current/Best: 15.73/ 20.21 GFLOPS | Progress: (12/20) | 12.76 s
+[Task 19/25] Current/Best: 15.09/ 20.21 GFLOPS | Progress: (16/20) | 15.73 s
+[Task 19/25] Current/Best: 2.70/ 22.70 GFLOPS | Progress: (20/20) | 18.54 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.02/ 14.93 GFLOPS | Progress: (4/20) | 3.37 s Done.
+[Task 20/25] Current/Best: 9.06/ 14.79 GFLOPS | Progress: (4/20) | 3.54 s Done.
Done.
-[Task 20/25] Current/Best: 10.16/ 14.93 GFLOPS | Progress: (8/20) | 6.80 s
-[Task 20/25] Current/Best: 2.31/ 16.12 GFLOPS | Progress: (12/20) | 10.75 s
-[Task 20/25] Current/Best: 12.42/ 16.12 GFLOPS | Progress: (16/20) | 14.46 s
-[Task 20/25] Current/Best: 13.11/ 21.67 GFLOPS | Progress: (20/20) | 16.55 s
+[Task 20/25] Current/Best: 9.98/ 14.79 GFLOPS | Progress: (8/20) | 7.14 s
+[Task 20/25] Current/Best: 2.31/ 16.44 GFLOPS | Progress: (12/20) | 11.15 s
+[Task 20/25] Current/Best: 12.32/ 16.44 GFLOPS | Progress: (16/20) | 15.10 s
+[Task 20/25] Current/Best: 13.00/ 21.56 GFLOPS | Progress: (20/20) | 17.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.60 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 21/25] Current/Best: 14.50/ 17.60 GFLOPS | Progress: (8/20) | 4.80 s
-[Task 21/25] Current/Best: 1.61/ 17.60 GFLOPS | Progress: (12/20) | 6.97 s
-[Task 21/25] Current/Best: 17.88/ 17.88 GFLOPS | Progress: (16/20) | 10.43 s
-[Task 21/25] Current/Best: 4.46/ 17.88 GFLOPS | Progress: (20/20) | 17.59 s
+[Task 21/25] Current/Best: 6.37/ 17.41 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 21/25] Current/Best: 14.39/ 17.41 GFLOPS | Progress: (8/20) | 5.00 s
+[Task 21/25] Current/Best: 1.61/ 17.41 GFLOPS | Progress: (12/20) | 7.21 s
+[Task 21/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (16/20) | 10.78 s
+[Task 21/25] Current/Best: 4.45/ 17.91 GFLOPS | Progress: (20/20) | 18.27 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.98 GFLOPS | Progress: (4/20) | 2.70 s
-[Task 22/25] Current/Best: 8.96/ 21.70 GFLOPS | Progress: (8/20) | 4.65 s
-[Task 22/25] Current/Best: 19.88/ 21.70 GFLOPS | Progress: (12/20) | 6.95 s
-[Task 22/25] Current/Best: 15.20/ 21.70 GFLOPS | Progress: (16/20) | 9.00 s
-[Task 22/25] Current/Best: 12.98/ 21.70 GFLOPS | Progress: (20/20) | 10.73 s Done.
+[Task 22/25] Current/Best: 2.69/ 16.81 GFLOPS | Progress: (4/20) | 2.79 s
+[Task 22/25] Current/Best: 9.19/ 21.13 GFLOPS | Progress: (8/20) | 4.81 s
+[Task 22/25] Current/Best: 19.44/ 21.13 GFLOPS | Progress: (12/20) | 7.18 s
+[Task 22/25] Current/Best: 14.55/ 21.13 GFLOPS | Progress: (16/20) | 9.28 s
+[Task 22/25] Current/Best: 14.94/ 21.13 GFLOPS | Progress: (20/20) | 11.05 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 16.55/ 20.18 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 23/25] Current/Best: 15.47/ 20.18 GFLOPS | Progress: (8/20) | 6.67 s
-[Task 23/25] Current/Best: 20.77/ 21.01 GFLOPS | Progress: (12/20) | 8.49 s
-[Task 23/25] Current/Best: 6.38/ 21.01 GFLOPS | Progress: (16/20) | 15.45 s
-[Task 23/25] Current/Best: 7.67/ 21.01 GFLOPS | Progress: (20/20) | 19.68 s Done.
+[Task 23/25] Current/Best: 17.19/ 19.96 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 23/25] Current/Best: 15.80/ 19.96 GFLOPS | Progress: (8/20) | 6.80 s
+[Task 23/25] Current/Best: 20.62/ 21.04 GFLOPS | Progress: (12/20) | 8.66 s
+[Task 23/25] Current/Best: 5.55/ 21.04 GFLOPS | Progress: (16/20) | 16.16 s
+[Task 23/25] Current/Best: 7.13/ 21.04 GFLOPS | Progress: (20/20) | 20.50 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.46/ 8.46 GFLOPS | Progress: (4/20) | 11.81 s
-[Task 24/25] Current/Best: 1.96/ 8.46 GFLOPS | Progress: (8/20) | 22.88 s
-[Task 24/25] Current/Best: 4.29/ 8.46 GFLOPS | Progress: (12/20) | 34.45 s Done.
+[Task 24/25] Current/Best: 8.24/ 8.24 GFLOPS | Progress: (4/20) | 11.91 s
+[Task 24/25] Current/Best: 3.23/ 8.24 GFLOPS | Progress: (8/20) | 23.26 s
+[Task 24/25] Current/Best: 3.90/ 8.24 GFLOPS | Progress: (12/20) | 34.02 s Done.
Done.
-[Task 24/25] Current/Best: 6.90/ 8.74 GFLOPS | Progress: (16/20) | 39.96 s
-[Task 24/25] Current/Best: 3.26/ 8.83 GFLOPS | Progress: (20/20) | 45.91 s Done.
+[Task 24/25] Current/Best: 7.09/ 8.25 GFLOPS | Progress: (16/20) | 39.80 s
+[Task 24/25] Current/Best: 3.08/ 8.75 GFLOPS | Progress: (20/20) | 46.09 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.52/ 2.92 GFLOPS | Progress: (4/20) | 11.61 s
-[Task 25/25] Current/Best: 5.56/ 7.83 GFLOPS | Progress: (8/20) | 22.91 s
-[Task 25/25] Current/Best: 5.93/ 7.83 GFLOPS | Progress: (12/20) | 34.21 s
-[Task 25/25] Current/Best: 5.76/ 9.23 GFLOPS | Progress: (16/20) | 35.97 s
-[Task 25/25] Current/Best: 2.88/ 9.23 GFLOPS | Progress: (20/20) | 46.66 s
+[Task 25/25] Current/Best: 1.52/ 2.58 GFLOPS | Progress: (4/20) | 11.70 s
+[Task 25/25] Current/Best: 4.94/ 7.29 GFLOPS | Progress: (8/20) | 23.08 s
+[Task 25/25] Current/Best: 5.59/ 7.29 GFLOPS | Progress: (12/20) | 34.43 s
+[Task 25/25] Current/Best: 5.45/ 8.57 GFLOPS | Progress: (16/20) | 36.34 s
+[Task 25/25] Current/Best: 2.88/ 8.57 GFLOPS | Progress: (20/20) | 47.03 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -972,8 +972,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 417.77566085002036, 'median': 417.7301799499219, 'std': 0.9381233133395673}
-unoptimized: {'mean': 495.8506218799994, 'median': 495.5960244999005, 'std': 0.9961609385082597}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 419.95983982000325, 'median': 419.8618299000145, 'std': 1.4574627417621062}
+unoptimized: {'mean': 505.915253750004, 'median': 505.9168230500063, 'std': 0.8558069739254331}
</pre></div>
</div>
</div>
@@ -987,7 +987,7 @@ 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 19.583 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 35.123 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python 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 bfb592cb8..5ced90435 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -518,7 +518,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.332e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.27e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index d632d72f2..9dd9cd9bc 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -478,7 +478,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x204ab590)), stage(b, placeholder(b, 0x4775ef0)), 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 [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x4629810)), stage(b, placeholder(b, 0x21ede770)), 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>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 450430244..13d434ddc 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>13:02.271</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:20.666</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,38 +331,38 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>10:19.583</p></td>
+<td><p>10:35.123</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>01:01.143</p></td>
+<td><p>01:03.098</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:46.422</p></td>
+<td><p>00:46.163</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:28.558</p></td>
+<td><p>00:29.305</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:24.930</p></td>
+<td><p>00:25.516</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
-<td><p>00:00.788</p></td>
+<tr class="row-even"><td><p><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></td>
+<td><p>00:00.728</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.693</p></td>
+<tr class="row-odd"><td><p><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></td>
+<td><p>00:00.536</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.154</p></td>
+<td><p>00:00.195</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
+<tr class="row-odd"><td><p><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></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
@@ -370,7 +370,7 @@
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
+<tr class="row-odd"><td><p><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></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 95245d88a..d8d04672c 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -533,7 +533,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000006
</pre></div>
</div>
@@ -585,7 +585,7 @@ compile and run this new schedule with the parallel operation applied:</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
-parallel: 0.000007
+parallel: 0.000006
</pre></div>
</div>
</div>
@@ -659,10 +659,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.78711999373627e-06 1.0
- naive 5.8932e-06 0.7567881328065211
-parallel 7.051700000000001e-06 0.9055594373365482
- vector 2.4635299999999998e-05 3.1635957863518103
+ numpy 7.010519998402742e-06 1.0
+ naive 5.9013000000000006e-06 0.8417777855771806
+parallel 6.1149000000000005e-06 0.8722462815016865
+ vector 2.45842e-05 3.5067584152960407
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -978,7 +978,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</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</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018628
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019532
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1021,7 +1021,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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: 3.410810
+none: 3.507196
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1088,7 +1088,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
-blocking: 0.313466
+blocking: 0.329147
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1149,7 +1149,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
-vectorization: 0.342670
+vectorization: 0.347269
@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], []),
@@ -1206,7 +1206,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
-loop permutation: 0.119944
+loop permutation: 0.136789
@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], []),
@@ -1284,7 +1284,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
-array packing: 0.111957
+array packing: 0.111678
@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], []),
@@ -1360,7 +1360,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
-block caching: 0.110606
+block caching: 0.114138
@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], []),
@@ -1429,7 +1429,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: 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. "
-parallelization: 0.145019
+parallelization: 0.148607
@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], []),
@@ -1491,13 +1491,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4108103351 1.0
- blocking 0.3134660292 0.09190368223474076
- vectorization 0.3426699868 0.10046585800261257
-loop permutation 0.1199437368 0.0351657597508961
- array packing 0.11195676619999999 0.032824096094665314
- block caching 0.11060611329999999 0.032428104301717844
- parallelization 0.1450192315 0.04251753022079085
+ none 3.5071963054 1.0
+ blocking 0.32914739159999995 0.09384914984462504
+ vectorization 0.347269327 0.09901622172255155
+loop permutation 0.1367886979 0.03900229299665594
+ array packing 0.1116779582 0.03184251706357309
+ block caching 0.1141378778 0.03254390911174915
+ parallelization 0.14860707099999998 0.04237204252615998
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1529,7 +1529,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.143 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.098 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.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">tensor_expr_get_started.py</span></code></a></p>