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 2022/08/03 01:44:15 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@1ca07438e0c42a33a734d5cec491caed58f39883)
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 fab4169fb deploying docs (apache/tvm@1ca07438e0c42a33a734d5cec491caed58f39883)
fab4169fb is described below
commit fab4169fb4a3a0fa781f36b376e1945c59977419
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Aug 3 01:44:09 2022 +0000
deploying docs (apache/tvm@1ca07438e0c42a33a734d5cec491caed58f39883)
---
docs/_sources/contribute/release_process.rst.txt | 44 +-
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1813 ++++----------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 120 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../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 | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../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/contribute/index.html | 1 +
docs/contribute/release_process.html | 69 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 16 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 32 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 20 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 40 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1813 ++++----------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 120 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
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 | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
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 | 22 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
125 files changed, 1609 insertions(+), 3976 deletions(-)
diff --git a/docs/_sources/contribute/release_process.rst.txt b/docs/_sources/contribute/release_process.rst.txt
index e2bf6455b..685b56cf1 100644
--- a/docs/_sources/contribute/release_process.rst.txt
+++ b/docs/_sources/contribute/release_process.rst.txt
@@ -51,7 +51,13 @@ Prepare the Release Notes
Release note contains new features, improvement, bug fixes, known issues and deprecation, etc. TVM provides `monthly dev report <https://discuss.tvm.ai/search?q=TVM%20Monthly%20%23Announcement>`_ collects developing progress each month. It could be helpful to who writes the release notes.
-It is recommended to open a Github issue to collect feedbacks for the release note draft before cutting the release branch.
+It is recommended to open a Github issue to collect feedbacks for the release note draft before cutting the release branch. See the scripts in ``tests/scripts/release`` for some starting points.
+
+
+Prepare the Release Candidate
+-----------------------------
+
+There may be some code changes necessary to the release branch before the release. Ensure all version numbers are up to date
Prepare the GPG Key
@@ -72,7 +78,7 @@ The last step is to update the KEYS file with your code signing key https://www.
cd svn-tvm
# edit KEYS file
svn ci --username $ASF_USERNAME --password "$ASF_PASSWORD" -m "Update KEYS"
- # update downloads.apache.org
+ # update downloads.apache.org (note that only PMC members can update the dist/release directory)
svn rm --username $ASF_USERNAME --password "$ASF_PASSWORD" https://dist.apache.org/repos/dist/release/tvm/KEYS -m "Update KEYS"
svn cp --username $ASF_USERNAME --password "$ASF_PASSWORD" https://dist.apache.org/repos/dist/dev/tvm/KEYS https://dist.apache.org/repos/dist/release/tvm/ -m "Update KEYS"
@@ -86,6 +92,7 @@ To cut a release candidate, one needs to first cut a branch using selected versi
git clone https://github.com/apache/tvm.git
cd tvm/
+ # Replace v0.6.0 with the relevant version
git branch v0.6.0
git push --set-upstream origin v0.6.0
@@ -111,8 +118,9 @@ Create source code artifacts,
.. code-block:: bash
- git clone git@github.com:apache/tvm.git apache-tvm-src-v0.6.0.rc0
- cd apache-tvm-src-v0.6.0.rc0
+ # Replace v0.6.0 with the relevant version
+ git clone git@github.com:apache/tvm.git apache-tvm-src-v0.6.0
+ cd apache-tvm-src-v0.6.0
git checkout v0.6
git submodule update --init --recursive
git checkout v0.6.0.rc0
@@ -120,7 +128,7 @@ Create source code artifacts,
find . -name ".git*" -print0 | xargs -0 rm -rf
cd ..
brew install gnu-tar
- gtar -czvf apache-tvm-src-v0.6.0.rc0.tar.gz apache-tvm-src-v0.6.0.rc0
+ gtar -czvf apache-tvm-src-v0.6.0.rc0.tar.gz apache-tvm-src-v0.6.0
Use your GPG key to sign the created artifact. First make sure your GPG is set to use the correct private key,
@@ -191,13 +199,35 @@ Remember to create a new release TAG (v0.6.0 in this case) on Github and remove
.. code-block:: bash
- git push --delete origin v0.6.0.rc2
+ git push --delete origin v0.6.0.rc2
Update the TVM Website
----------------------
-The website repository is located at `https://github.com/apache/tvm-site <https://github.com/apache/tvm-site>`_. Modify the download page to include the release artifacts as well as the GPG signature and SHA hash.
+The website repository is located at `https://github.com/apache/tvm-site <https://github.com/apache/tvm-site>`_. Modify the download page to include the release artifacts as well as the GPG signature and SHA hash. Since TVM's docs are continually updated, upload a fixed version of the release docs. If CI has deleted the docs from the release by the time you go to update the website, you can restart the CI build for the release branch on Jenkins. See the example code below for a starting point
+
+.. code-block:: bash
+
+ git clone https://github.com/apache/tvm-site.git
+ pushd tvm-site
+ git checkout asf-site
+ pushd docs
+
+ # make release docs directory
+ mkdir v0.9.0
+ pushd v0.9.0
+
+ # download the release docs from CI
+ # find this URL by inspecting the CI logs for the most recent build of the release branch
+ curl -LO https://tvm-jenkins-artifacts-prod.s3.us-west-2.amazonaws.com/tvm/v0.9.0/1/docs/docs.tgz
+ tar xf docs.tgz
+ rm docs.tgz
+
+ # add the docs and push
+ git add .
+ git commit -m"Add v0.9.0 docs"
+ git push
Post the Announcement
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index d7c64dadb..e8b7a50c9 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.696 seconds)
+ **Total running time of the script:** ( 1 minutes 5.629 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
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 2f5e2ce51..5098ad522 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip45a02494-9a29-4649-97c1-bd31de6fc96e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipd607a7e7-9988-4aea-969c-4497b4227772 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 e80988046..368449667 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ 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]
15%|#5 | 6.33M/41.5M [00:00<00:00, 50.7MB/s]
27%|##6 | 11.2M/41.5M [00:00<00:01, 27.3MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:01, 26.2MB/s]
45%|####5 | 18.8M/41.5M [00:00<00:00, 31.9MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 31.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 43.1MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 44.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 37.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 44.5MB/s]
25%|##5 | 10.6M/41.5M [00:00<00:00, 41.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 39.0MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 44.8MB/s]
64%|######4 | 26.7M/41.5M [00:00<00:00, 39.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.4MB/s]
96%|#########5| 39.7M/41.5M [00:01<00:00, 41.9MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.0MB/s]
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 c8f857962..4663bb2d3 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ 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]
10%|# | 4.57M/44.7M [00:00<00:00, 47.8MB/s]
20%|## | 9.13M/44.7M [00:00<00:00, 46.4MB/s]
69%|######8 | 30.6M/44.7M [00:00<00:00, 127MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 130MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
41%|####1 | 18.4M/44.7M [00:00<00:00, 193MB/s]
87%|########7 | 38.9M/44.7M [00:00<00:00, 206MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 210MB/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 79f63fbc0..53211bafd 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.230 seconds)
+ **Total running time of the script:** ( 1 minutes 5.528 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 218436e58..9952dbe4c 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
=================
-**05:26.251** total execution time for **how_to_compile_models** files:
+**05:12.806** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:16.230 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:05.629 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:07.696 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:05.528 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.243 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.222 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:28.215 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.673 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.652 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.401 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.458 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:24.708 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.202 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.940 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.423 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.066 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.457 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.411 | 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 799d0bd84..ba7bd8b9e 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
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2673 16.1593 17.0296 15.8406 0.3933
+ 16.3079 15.8600 20.0648 15.7761 1.2564
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 aaa929633..12b4f5714 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
@@ -123,7 +123,7 @@ 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]
10%|# | 17.7M/170M [00:00<00:00, 186MB/s]
25%|##4 | 41.8M/170M [00:00<00:00, 225MB/s]
39%|###8 | 65.6M/170M [00:00<00:00, 236MB/s]
52%|#####1 | 88.0M/170M [00:00<00:00, 232MB/s]
66%|######6 | 112M/170M [00:00<00:00, 239MB/s]
80%|#######9 | 135M/170M [00:00<00:00, 168MB/s]
90%|######### | 154M/170M [00:01<00:00, 108MB/s]
99%|#########8| 168M/170M [00:01<00:00, 96.6MB/s]
100%|##########| 170M/170M [00:01<00:00, 138MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 3.34M/170M [00:00<00:04, 34.9MB/s]
5%|4 | 7.77M/170M [00:00<00:04, 41.7MB/s]
16%|#6 | 27.8M/170M [00:00<00:01, 118MB/s]
30%|##9 | 50.9M/170M [00:00<00:00, 167MB/s]
44%|####3 | 74.6M/170M [00:00<00:00, 197MB/s]
58%|#####7 | 97.8M/170M [00:00<00:00, 212MB/s]
72%|#######1 | 122M/170M [00:00<00:00, 225MB/s]
87%|########7 | 148M/170M [00:00<00:00, 241MB/s]
100%|##########| 170M/170M [00:00<00:00, 201MB/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').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 2.419 seconds)
+ **Total running time of the script:** ( 2 minutes 59.581 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 6af16f3a3..fb8a4eb9f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 160MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 177MB/s]
@@ -412,7 +412,7 @@ 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)
- 90.4510 90.3276 94.6396 90.1403 0.4694
+ 90.3224 90.2395 95.7022 90.0782 0.5620
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.305 seconds)
+ **Total running time of the script:** ( 1 minutes 9.631 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 d93686bfc..9b588c6ab 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
@@ -439,7 +439,7 @@ 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)
- 119.9869 119.9461 121.5897 119.1387 0.4557
+ 120.8555 120.0777 126.9296 118.9443 1.5509
@@ -476,7 +476,7 @@ 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 52.303 seconds)
+ **Total running time of the script:** ( 1 minutes 55.391 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 0dac6413e..322caaa99 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 43.819 seconds)
+ **Total running time of the script:** ( 1 minutes 37.237 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 dd8a136cc..bd3a50b3e 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
@@ -158,7 +158,7 @@ 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]
4%|4 | 5330/132723 [00:00<00:02, 52960.64KB/s]
10%|9 | 12875/132723 [00:00<00:01, 66151.29KB/s]
15%|#4 | 19494/132723 [00:00<00:02, 56166.07KB/s]
20%|## | 27062/132723 [00:00<00:01, 63108.88KB/s]
26%|##6 | 34659/132723 [00:00<00:01, 67341.71KB/s]
31%|###1 | 41529/132723 [00:00<00:01, 65260.05KB/s]
37%|###6 | 48589/132723 [00:00<00:01, 66907.09KB/s]
42%|####1 | 55354/132723 [00:00<00:01, 50716.19KB/s]
47%|####7 | 62961/132723 [00:01<00:01, 57008.74KB/s]
52%|#####2 | 69228/132723 [00:01<00:01, 49574.23KB/s]
58%|#####7 | 76763/132723 [00:01<00:01, 55777.07KB/s]
62%|######2 | 82871/132723 [00:01<00:00, 56106.27KB/s]
68%|######8 | 90319/132723 [00:01<00:00, 60958.46KB/s]
74%|#######3 | 98029/132723 [00:01<00:00, 65378.89KB/s]
79%|#######8 | 104844/132723 [00:01<00:00, 56813.78KB/s]
85%|########4
| 112450/132723 [00:01<00:00, 61749.52KB/s]
90%|########9 | 118973/132723 [00:02<00:00, 41586.33KB/s]
94%|#########3| 124213/132723 [00:02<00:00, 42666.87KB/s]
99%|#########9| 131804/132723 [00:02<00:00, 49982.13KB/s]
100%|##########| 132723/132723 [00:02<00:00, 55122.45KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3960/132723 [00:00<00:03, 39168.78KB/s]
9%|8 | 11483/132723 [00:00<00:02, 60276.99KB/s]
13%|#3 | 17521/132723 [00:00<00:02, 56717.87KB/s]
19%|#9 | 25800/132723 [00:00<00:01, 66611.02KB/s]
26%|##5 | 34048/132723 [00:00<00:01, 72187.59KB/s]
32%|###1 | 42292/132723 [00:00<00:01, 75613.34KB/s]
38%|###8 | 50596/132723 [00:00<00:01, 78011.57KB/s]
44%|####4 | 58800/132723 [00:00<00:00, 79282.19KB/s]
51%|##### | 67079/132723 [00:00<00:00, 80366.26KB/s]
57%|#####6 | 75352/132723 [00:01<00:00, 81091.19KB/s]
63%|######3 | 83670/132723 [00:01<00:00, 81727.02KB/s]
69%|######9 | 91977/132723 [00:01<00:00, 82132.04KB/s]
75%|#######5 | 100196/132723 [00:01<00:00, 59734.12KB/s]
82%|########1 | 108481/132723 [00:01<00:00, 65260.20KB/s]
87%|########7 | 115758/132723 [00:01<00:00, 61216.51KB/s]
93%|########
#3| 123957/132723 [00:01<00:00, 66386.29KB/s]
100%|#########9| 132373/132723 [00:01<00:00, 71046.39KB/s]
100%|##########| 132723/132723 [00:01<00:00, 70445.75KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 36.163 seconds)
+ **Total running time of the script:** ( 2 minutes 35.378 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 eafd18291..9fad0e938 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
@@ -5,24 +5,24 @@
Computation times
=================
-**11:40.120** total execution time for **how_to_deploy_models** files:
+**11:30.764** 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``) | 03:02.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:59.581 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:36.163 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:35.378 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:52.303 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:55.391 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:43.819 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:37.237 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.305 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:09.631 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.243 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.759 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.625 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.219 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.237 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.562 | 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 cf0e1beb7..b04b8344d 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
@@ -476,7 +476,7 @@ 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.zipc1b7ff4e-769a-43e6-b403-876f4d0c3d27 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip54806edd-ebeb-4204-9236-3f733f76ad76 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index a6cee904d..c1991c56b 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
=================
-**00:41.124** total execution time for **how_to_extend_tvm** files:
+**00:40.012** 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``) | 00:37.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:36.946 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.225 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.147 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.967 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.912 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 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 739f65a57..76867827c 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
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6530us [6530us] (45.79%; 45.79%)
- FoldScaleAxis: 7731us [6us] (54.21%; 54.21%)
- FoldConstant: 7726us [1595us] (54.17%; 99.93%)
- InferType: 6131us [6131us] (42.99%; 79.35%)
+ InferType: 6516us [6516us] (45.89%; 45.89%)
+ FoldScaleAxis: 7683us [5us] (54.11%; 54.11%)
+ FoldConstant: 7677us [1587us] (54.07%; 99.93%)
+ InferType: 6090us [6090us] (42.89%; 79.33%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6128us [6128us] (44.61%; 44.61%)
- FoldScaleAxis: 7609us [5us] (55.39%; 55.39%)
- FoldConstant: 7605us [1567us] (55.36%; 99.94%)
- InferType: 6038us [6038us] (43.95%; 79.39%)
+ InferType: 6131us [6131us] (44.52%; 44.52%)
+ FoldScaleAxis: 7641us [5us] (55.48%; 55.48%)
+ FoldConstant: 7637us [1595us] (55.45%; 99.94%)
+ InferType: 6041us [6041us] (43.87%; 79.11%)
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 1b90dd4c0..262053270 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
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 50.269086 ms
+ Convolution: 54.203462 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 4573ad05a..9e1f1cdc0 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
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.024940 ms
+ conv2d with tensor core: 6.833399 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 5e379f4db..edbc85359 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019196
- Baseline: 3.299340
+ Numpy running time: 0.018883
+ Baseline: 3.428025
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.319600
+ Opt1: 0.316967
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.348555
+ Opt2: 0.338233
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.119710
+ Opt3: 0.117703
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110977
+ Opt4: 0.111367
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111555
+ Opt5: 0.112490
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145087
+ Opt6: 0.145839
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 5fe975096..2dc4a4883 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
=================
-**00:34.635** total execution time for **how_to_optimize_operators** files:
+**00:34.851** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.342 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.548 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.239 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.246 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.053 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.057 | 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 5f48b3220..7de638497 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
=================
-**06:09.810** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:54.339** 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``) | 03:22.207 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:12.135 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.650 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.658 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.311 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.015 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:20.707 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.143 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.003 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.705 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.932 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.683 | 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 f9425f48f..10169c54c 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
@@ -240,777 +240,192 @@ 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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 32) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*784)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*144)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 48)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 504), 48)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 40), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((threadIdx.x_1 < 48) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 30), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 30), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 8), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = 0f32
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 112), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 168), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 336), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 504), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 728), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 840), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (rc.inner: int32, 0, 8) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 720)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 720)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 721)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 721)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 722)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 722)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 675)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 675)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 676)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 676)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 677)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 677)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 684)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 684)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 685)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 685)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 783)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 783)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 785)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 785)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 846)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 846)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 847)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 847)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 848)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 848)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 792)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 792)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 793)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 793)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 794)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 794)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 855)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 855)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 856)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 856)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 857)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 857)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 801)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 801)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 802)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 802)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 803)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 803)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 864)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 864)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 865)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 865)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 866)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 866)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 873)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 873)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 874)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 874)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 875)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 875)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 918)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 918)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 919)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 919)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 920)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 920)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 927)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 927)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 928)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 928)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 929)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 929)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 936)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 936)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 937)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 937)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 938)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 938)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 999)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 999)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1000)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1000)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1001)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1001)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
}
}
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 392)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
- }
+ compute[((blockIdx.x*392) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
@@ -1064,7 +479,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.415 ms
+ Execution time of this operator: 0.189 ms
@@ -1115,18 +530,18 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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=8)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, 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=1)
+ 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=7)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
@@ -1136,13 +551,13 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
- compute_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_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1168,7 +583,7 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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", 1024)
+ 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, "unroll_explicit", True)
CUDA source code:
@@ -1187,739 +602,143 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define uint64_t unsigned long long
#endif
extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[768];
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- if (((int)threadIdx.x) < 40) {
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + (((((int)threadIdx.x) + 24) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((4 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + (((((int)threadIdx.x) + 5) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + (((((int)threadIdx.x) + 11) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 8) {
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = 0.000000e+00f;
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 720)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 720)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 721)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 721)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 722)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 722)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 666)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 666)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 729)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 729)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 675)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 675)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 676)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 676)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 677)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 677)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 738)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 738)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 684)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 684)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 685)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 685)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 686)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 686)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 747)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 747)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 783)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 783)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 784)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 784)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 785)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 785)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 846)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 846)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 847)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 847)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 848)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 848)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 792)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 792)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 793)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 793)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 794)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 794)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 855)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 855)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 856)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 856)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 857)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 857)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 801)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 801)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 802)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 802)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 803)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 803)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 864)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 864)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 865)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 865)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 866)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 866)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 810)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 810)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 873)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 873)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 874)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 874)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 875)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 875)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 918)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 918)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 919)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 919)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 920)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 920)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 981)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 981)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 927)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 927)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 928)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 928)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 929)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 929)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 990)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 990)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 936)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 936)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 937)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 937)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 938)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 938)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 999)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 999)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1000)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1000)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1001)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1001)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
- }
+ compute[((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
@@ -1980,7 +799,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 22.207 seconds)
+ **Total running time of the script:** ( 3 minutes 12.135 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 699347e6f..20ac4cf62 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
@@ -647,7 +647,7 @@ 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)
- 9.8633 9.8669 9.8715 9.8516 0.0085
+ 9.7879 9.7805 9.8337 9.7494 0.0348
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 f2143f887..66a8eaa31 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
@@ -666,7 +666,7 @@ 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)
- 766.8072 766.7924 766.9597 766.6695 0.1189
+ 753.6852 753.3992 754.7367 752.9197 0.7689
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.650 seconds)
+ **Total running time of the script:** ( 1 minutes 21.658 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 dc973d4c3..8e15dba6c 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
@@ -397,12 +397,12 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), 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, 32) "parallel" {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*16))
+ for (i.outer.inner: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
{
compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
@@ -422,78 +422,52 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 64) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_2: int32 = ((i.outer.inner*1024) + (i.inner*16))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_4: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
+ let cse_var_18: int32 = ((i.outer.inner*128) + (i.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
+ let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
+ let cse_var_22: int32 = ((i0.inner*512) + cse_var_23)
+ compute[ramp(cse_var_22, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_23) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -549,7 +523,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.833 ms
+ Execution time of this operator: 3.610 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 25fb55756..6293c2e91 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:46.202** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.570** 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``) | 00:46.166 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.535 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 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``) | 00:00.005 | 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 c6ad4aab8..141d96280 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
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 192.42/192.42 result: MeasureResult(costs=(0.0012030982222222223,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0964510440826416, timestamp=1659479230.9060364) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/192.42 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 80.85/80.85 result: MeasureResult(costs=(0.002863335142857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8809525966644287, timestamp=1659484687.395197) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/80.85 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
@@ -1280,8 +1280,8 @@ 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, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.47/260.47 result: MeasureResult(costs=(0.0008887805083798882,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4137368202209473, timestamp=1659479231.8076637) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.10/260.10 result: MeasureResult(costs=(0.0008900587900552485,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7123539447784424, timestamp=1659484688.2929778) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.10 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
@@ -1404,7 +1404,7 @@ 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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.10 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
@@ -1527,7 +1527,7 @@ 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, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.10 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
@@ -1650,9 +1650,9 @@ 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, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.29/260.47 result: MeasureResult(costs=(0.04377225825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.842933177947998, timestamp=1659479236.371284) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.36/260.47 result: MeasureResult(costs=(0.06892603624999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.579137086868286, timestamp=1659479237.6056433) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.46/260.10 result: MeasureResult(costs=(0.042374166500000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8468067646026611, timestamp=1659484692.840606) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/260.10 result: MeasureResult(costs=(0.0693154735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.531064510345459, timestamp=1659484694.0785117) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.10 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
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.00/260.47 result: MeasureResult(costs=(0.008268678357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2928235530853271, timestamp=1659479248.6388752) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.01/260.10 result: MeasureResult(costs=(0.008265518142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3182411193847656, timestamp=1659484705.1653576) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.10 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
@@ -1794,7 +1794,7 @@ 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, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.10 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
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001322
+ Time cost of this operator: 0.001220
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 0807de211..cdbfd9839 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
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.4 98.731 (1, 2, 10, 10, 3) 2 1 [313.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.054 0.962 (1, 6, 10, 10) 1 1 [3.054]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.307 (1, 1, 10, 10, 3) 1 1 [0.974]
- Total_time - 317.428 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.8 98.693 (1, 2, 10, 10, 3) 2 1 [309.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.147 1.003 (1, 6, 10, 10) 1 1 [3.147]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.305 (1, 1, 10, 10, 3) 1 1 [0.956]
+ Total_time - 313.903 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 219.9 98.635 (1, 1, 10, 10, 6) 2 1 [219.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.2 0.987 (1, 6, 10, 10) 1 1 [2.2]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.378 (1, 3, 10, 10, 1) 1 1 [0.843]
- Total_time - 222.943 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.438 96.676 (1, 6, 10, 10, 1) 2 1 [80.438]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.792 2.153 (1, 6, 10, 10) 1 1 [1.792]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 1.171 (1, 1, 10, 10, 3) 1 1 [0.974]
+ Total_time - 83.203 - - - - -
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 2b9beaeba..e0b31cecc 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/tmpijas024t/images/random'
+ '/tmp/tmphy0jj1fy/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpijas024t/images/target contains 8144 images
- /tmp/tmpijas024t/images/random contains 5000 images
+ /tmp/tmphy0jj1fy/images/target contains 8144 images
+ /tmp/tmphy0jj1fy/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 56s - loss: 0.2151 - accuracy: 0.9280 - val_loss: 0.1213 - val_accuracy: 0.9615
+ 328/328 - 56s - loss: 0.2103 - accuracy: 0.9276 - val_loss: 0.1370 - val_accuracy: 0.9562
Epoch 2/3
- 328/328 - 53s - loss: 0.1029 - accuracy: 0.9623 - val_loss: 0.1111 - val_accuracy: 0.9626
+ 328/328 - 52s - loss: 0.0977 - accuracy: 0.9636 - val_loss: 0.1129 - val_accuracy: 0.9641
Epoch 3/3
- 328/328 - 52s - loss: 0.0685 - accuracy: 0.9750 - val_loss: 0.1541 - val_accuracy: 0.9505
+ 328/328 - 52s - loss: 0.0685 - accuracy: 0.9738 - val_loss: 0.1673 - val_accuracy: 0.9377
- <keras.callbacks.History object at 0x7efef1110b90>
+ <keras.callbacks.History object at 0x7f82503de210>
@@ -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:** ( 5 minutes 28.119 seconds)
+ **Total running time of the script:** ( 5 minutes 33.153 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 c25aa1322..6ff62b825 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
@@ -5,16 +5,16 @@
Computation times
=================
-**06:21.916** total execution time for **how_to_work_with_microtvm** files:
+**06:25.683** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:28.119 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:33.153 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.617 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.655 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.852 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.634 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.326 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.240 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 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 ceea48bc1..c401e14d9 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:42.151** total execution time for **how_to_work_with_relay** files:
+**00:42.922** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.822 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.727 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.812 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.958 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.509 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:02.230 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 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 2d1acce20..3ca8408da 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
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7efe76945e60>
+ <function my_cuda_math_rule at 0x7f81b3d785f0>
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 53efd2f85..08bf444ac 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
=================
-**00:04.107** total execution time for **how_to_work_with_schedules** files:
+**00:04.127** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.896 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.908 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.976 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.978 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.533 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.541 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.515 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.516 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.103 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 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_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 c9ac37b3f..fb5572215 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ 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/tmp_73auzf3/input0.cc'\nsource_filename = \"/tmp/tmp_73auzf3/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/tmps095mswj/input0.cc'\nsource_filename = \"/tmp/tmps095mswj/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 1dc9d8a48..bdd711e19 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
=================
-**00:21.797** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.734** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.791 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.727 | 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 c0b36267a..88c4bef97 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 23.54s!
+ resnet18_v1 inference graph built in 23.45s!
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 991f52213..9c4e37ab5 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 16.55s!
+ yolov3-tiny inference graph built in 16.13s!
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 fb833a9b4..91889d556 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
=================
-**01:33.195** total execution time for **topic_vta_tutorials_frontend** files:
+**01:33.917** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.504 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.274 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.692 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.642 | 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 5d638955d..e2830583f 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
=================
-**00:03.293** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.255** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.900 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.848 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.393 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.407 | 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 c1eff5ae5..0f01e3fec 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
=================
-**00:00.700** total execution time for **topic_vta_tutorials** files:
+**00:00.716** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.374 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.380 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.326 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.336 | 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 bd1f29e0c..a1a336d2e 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.208 ms
+ Execution time of this operator: 94.031 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index de8026c6b..68cd15203 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 8.88/8.88 result: MeasureResult(costs=(0.0302405864,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6165728569030762, timestamp=1659477976.4120898) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.94/8.88 result: MeasureResult(costs=(0.0914235504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6181211471557617, timestamp=1659477978.56386) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.0227730018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6103503704071045, timestamp=1659477979.1305115) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.87/11.79 result: MeasureResult(costs=(0.14388056200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.428006410598755, timestamp=1659477982.1260848) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.65/11.79 result: MeasureResult(costs=(0.07363607,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.319868564605713, timestamp=1659477983.5741856) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.76/11.79 result: MeasureResult(costs=(0.1524592394,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6105194091796875, timestamp=1659477986.7659535) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.79 result: MeasureResult(costs=(0.307379643,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.035019159317017, timestamp=1659477991.8476741) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.25/11.79 result: MeasureResult(costs=(0.026182003600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5667905807495117, timestamp=1659477992.4284546) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.89/11.79 result: MeasureResult(costs=(0.1420826808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3733842372894287, timestamp=1659477994.9220536) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.49/11.79 result: MeasureResult(costs=(0.1079180346,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8324904441833496, timestamp=1659477996.8122902) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.53/10.53 result: MeasureResult(costs=(0.0255032078,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5398743152618408, timestamp=1659483456.5337129) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.92/10.53 result: MeasureResult(costs=(0.0919450734,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6158719062805176, timestamp=1659483458.6942506) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.0227363286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6014094352722168, timestamp=1659483459.2596972) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.85/11.81 result: MeasureResult(costs=(0.1451020456,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.441189765930176, timestamp=1659483462.270703) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.67/11.81 result: MeasureResult(costs=(0.0731474764,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3007020950317383, timestamp=1659483463.7008047) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.77/11.81 result: MeasureResult(costs=(0.1513506104,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5422887802124023, timestamp=1659483466.8076324) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.81 result: MeasureResult(costs=(0.308321106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.055330514907837, timestamp=1659483471.9059725) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.78/11.81 result: MeasureResult(costs=(0.0274402584,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5829212665557861, timestamp=1659483472.5071592) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.69/11.81 result: MeasureResult(costs=(0.15905891879999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.64192795753479, timestamp=1659483475.268641) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.76/11.81 result: MeasureResult(costs=(0.09741225299999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6625261306762695, timestamp=1659483476.989076) [('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 3c1456376..6ea56cd2e 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 495.4871293999895, 'median': 495.59110714999406, 'std': 0.7418536908477463}
+ {'mean': 493.81363693999447, 'median': 493.41480750001665, 'std': 1.7404822562804898}
@@ -563,30 +563,30 @@ 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: 17.55/ 17.55 GFLOPS | Progress: (4/20) | 6.34 s
[Task 1/25] Current/Best: 6.16/ 17.55 GFLOPS | Progress: (8/20) | 9.35 s
[Task 1/25] Current/Best: 11.48/ 22.77 GFLOPS | Progress: (12/20) | 11.78 s
[Task 1/25] Current/Best: 16.82/ 22.82 GFLOPS | Progress: (16/20) | 13.46 s
[Task 1/25] Current/Best: 11.62/ 23.81 GFLOPS | Progress: (20/20) | 15.20 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.24/ 13.06 GFLOPS | Progress: (4/20) | 3.65 s
[Task 2/25] Current/Best: 13.93/ 18.30 GFLOPS | Progress: (8/20) | 4.96 s
[Task 2/25] Current/Best: 20.89/ 20.89 GFLOPS | Progress: (12/20) | 6.27 s
[Task 2/25] Current/Best: 12.71/ 20.89 GFLOPS | Progress: (16/20) | 7.52 s
[Task 2/25] Current/Best: 19.96/ 20.89 GFLOPS | Progress: (20/20) | 9.08 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/ 10.50 GFLOPS | Progress: (4/20) | 5.88 s
[Task 3/25] Current/Best: 15.54/ 16.86 GFLOPS | Progress: (8/20) | 7.81 s
[Task 3/25] Current/Best: 14.87/ 16.86 GFLOPS | Progress: (12/20) | 9.57 s
[Task 3/25] Current/Best: 7.21/ 23.73 GFLOPS | Progress: (16/20) | 11.49 s
[Task 3/25] Current/Best: 11.97/ 23.73 GFLOPS | Progress: (20/20) | 16.01 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.39/ 20.15 GFLOPS | Progress: (4/20) | 2.42 s
[Task 4/25] Current/Best: 6.87/ 20.15 GFLOPS | Progress: (8/20) | 6.74 s
[Task 4/25] Current/Best: 22.14/ 22.14 GFLOPS | Progress: (12/20) | 11.20 s
[Task 4/25] Current/Best: 17.40/ 22.14 GFLOPS | Progress: (16/20) | 13.40 s
[Task 4/25] Current/Best: 13.47/ 22.14 GFLOPS | Progress: (20/20) | 15.37 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.62/ 10.46 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.75/ 13.19 GFLOPS | Progress: (8/20) | 4.69 s
[Task 5/25] Current/Best: 10.97/ 17.72 GFLOPS | Progress: (12/20) | 7.78 s
[Task 5/25] Current/Best: 11.84/ 22.47 GFLOPS | Progress: (16/20) | 9.24 s
[Task 5/25] Current/Best: 11.93/ 22.47 GFLOPS | Progress: (20/20) | 11.10 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.23/ 20.79 GFLOPS | Progress: (4/20) | 3.96 s
[Task 6/25] Current/Best: 19.01/ 20.79 GFLOPS | Progress: (8/20) | 5.71 s
[Task 6/25] Current/Best: 13.22/ 20.79 GFLOPS | Progress: (12/20) | 7.62 s
[Task 6/25] Current/Best: 20.01/ 20.79 GFLOPS | Progress: (16/20) | 9.86 s
[Task 6/25] Current/Best: 3.73/ 20.79 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: 11.19/ 12.37 GFLOPS | Progress: (4/20) | 3.59 s
[Task 7/25] Current/Best: 20.26/ 21.01 GFLOPS | Progress: (8/20) | 5.12 s
[Task 7/25] Current/Best: 15.89/ 21.01 GFLOPS | Progress: (12/20) | 7.06 s
[Task 7/25] Current/Best: 12.22/ 21.01 GFLOPS | Progress: (16/20) | 9.11 s
[Task 7/25] Current/Best: 6.36/ 21.68 GFLOPS | Progress: (20/20) | 11.59 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.26/ 13.84 GFLOPS | Progress: (4/20) | 2.96 s
[Task 8/25] Current/Best: 9.67/ 13.84 GFLOPS | Progress: (8/20) | 7.66 s
[Task 8/25] Current/Best: 12.93/ 13.84 GFLOPS | Progress: (12/20) | 13.78 s
[Task 8/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (16/20) | 15.85 s
[Task 8/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (20/20) | 22.34 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.38/ 15.55 GFLOPS | Progress: (4/20) | 11.95 s
[Task 9/25] Current/Best: 23.35/ 23.35 GFLOPS | Progress: (8/20) | 13.74 s
[Task 9/25] Current/Best: 8.26/ 23.35 GFLOPS | Progress: (12/20) | 16.11 s
[Task 9/25] Current/Best: 18.04/ 23.35 GFLOPS | Progress: (16/20) | 18.75 s
[Task 9/25] Current/Best: 9.08/ 23.35 GFLOPS | Progress: (20/20) | 26.53 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (4/20) | 2.61 s
[Task 10/25] Current/Best: 15.54/ 18.21 GFLOPS | Progress: (8/20) | 4.22 s
[Task 10/25] Current/Best: 12.62/ 18.87 GFLOPS | Progress: (12/20) | 5.75 s
[Task 10/25] Current/Best: 19.13/ 20.41 GFLOPS | Progress: (16/20) | 6.86 s
[Task 10/25] Current/Best: 8.82/ 20.41 GFLOPS | Progress: (20/20
) | 8.39 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.23/ 18.14 GFLOPS | Progress: (4/20) | 3.35 s
[Task 11/25] Current/Best: 16.43/ 18.14 GFLOPS | Progress: (8/20) | 6.08 s
[Task 11/25] Current/Best: 17.22/ 18.14 GFLOPS | Progress: (12/20) | 8.12 s
[Task 11/25] Current/Best: 13.47/ 21.18 GFLOPS | Progress: (16/20) | 10.91 s
[Task 11/25] Current/Best: 19.36/ 21.54 GFLOPS | Progress: (20/20) | 12.92 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.73/ 18.00 GFLOPS | Progress: (4/20) | 5.40 s
[Task 12/25] Current/Best: 5.20/ 18.00 GFLOPS | Progress: (8/20) | 9.12 s
[Task 12/25] Current/Best: 18.64/ 19.10 GFLOPS | Progress: (12/20) | 11.13 s
[Task 12/25] Current/Best: 15.04/ 19.10 GFLOPS | Progress: (16/20) | 13.92 s
[Task 12/25] Current/Best: 15.11/ 19.10 GFLOPS | Progress: (20/20) | 15.87 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.20/ 17.24 GFLOPS | Progress: (4/20) | 3.71 s
[Task 13/25] Current/Best: 15.59/ 20.74 GFLOPS | Progress: (8/20) | 6.16 s
[Task 13/25] Current/Best: 19.67/ 21.41 GFLOPS | Progress: (12/20) | 9.04 s
[Task 13/25] Current/Best: 12.21/ 21.41 GFLOPS | Progress: (16/20) | 12.41 s
[Task 13/25] Current/Best: 18.22/ 21.41 GFLOPS | Progress: (20/20) | 14.63 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.68/ 13.68 GFLOPS | Progress: (4/20) | 3.37 s
[Task 14/25] Current/Best: 6.12/ 13.68 GFLOPS | Progress: (8/20) | 5.53 s
[Task 14/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (12/20) | 8.05 s
[Task 14/25] Current/Best: 16.29/ 20.58 GFLOPS | Progress: (16/20) | 9.71 s Done.
-
[Task 14/25] Current/Best: 16.72/ 20.58 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: 16.17/ 17.68 GFLOPS | Progress: (4/20) | 2.73 s
[Task 15/25] Current/Best: 14.26/ 18.05 GFLOPS | Progress: (8/20) | 4.06 s
[Task 15/25] Current/Best: 10.35/ 22.35 GFLOPS | Progress: (12/20) | 6.13 s
[Task 15/25] Current/Best: 20.39/ 22.35 GFLOPS | Progress: (16/20) | 9.61 s
[Task 15/25] Current/Best: 9.67/ 22.35 GFLOPS | Progress: (20/20) | 10.63 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (4/20) | 2.99 s
[Task 16/25] Current/Best: 3.04/ 20.55 GFLOPS | Progress: (8/20) | 4.62 s
[Task 16/25] Current/Best: 19.11/ 20.55 GFLOPS | Progress: (12/20) | 5.84 s
[Task 16/25] Current/Best: 18.13/ 20.55 GFLOPS | Progress: (16/20) |
7.18 s
[Task 16/25] Current/Best: 9.94/ 22.16 GFLOPS | Progress: (20/20) | 9.24 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.65/ 18.60 GFLOPS | Progress: (4/20) | 4.75 s
[Task 17/25] Current/Best: 14.40/ 23.05 GFLOPS | Progress: (8/20) | 7.52 s
[Task 17/25] Current/Best: 16.74/ 23.05 GFLOPS | Progress: (12/20) | 9.57 s
[Task 17/25] Current/Best: 17.45/ 23.05 GFLOPS | Progress: (16/20) | 11.69 s
[Task 17/25] Current/Best: 10.01/ 23.05 GFLOPS | Progress: (20/20) | 13.84 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.41/ 18.09 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 10.52/ 19.00 GFLOPS | Progress: (8/20) | 7.14 s
[Task 18/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (12/20) | 9.06 s
[Task 18/25] Current/Best: 9.96/ 19.15 GFLOPS | Progress: (16/20) | 12.60 s
[Task 18/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (20/20) | 14.12 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.09/ 20.30 GFLOPS | Progress: (4/20) | 6.04 s
[Task 19/25] Current/Best: 2.61/ 20.30 GFLOPS | Progress: (8/20) | 9.28 s
[Task 19/25] Current/Best: 19.47/ 21.45 GFLOPS | Progress: (12/20) | 12.12 s
[Task 19/25] Current/Best: 15.31/ 21.45 GFLOPS | Progress: (16/20) | 14.90 s
[Task 19/25] Current/Best: 2.70/ 23.38 GFLOPS | Progress: (20/20) | 17.68 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.87/ 15.15 GFLOPS | Progress: (4/20) | 3.35 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 6.29 s
[Task 1/25] Current/Best: 6.16/ 17.53 GFLOPS | Progress: (8/20) | 9.32 s
[Task 1/25] Current/Best: 11.51/ 22.74 GFLOPS | Progress: (12/20) | 11.75 s
[Task 1/25] Current/Best: 16.72/ 22.84 GFLOPS | Progress: (16/20) | 13.44 s
[Task 1/25] Current/Best: 11.58/ 23.68 GFLOPS | Progress: (20/20) | 15.17 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.32/ 13.14 GFLOPS | Progress: (4/20) | 3.83 s
[Task 2/25] Current/Best: 13.76/ 17.74 GFLOPS | Progress: (8/20) | 5.16 s
[Task 2/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (12/20) | 6.52 s
[Task 2/25] Current/Best: 12.51/ 21.35 GFLOPS | Progress: (16/20) | 7.79 s
[Task 2/25] Current/Best: 17.77/ 21.35 GFLOPS | Progress: (20/20) | 9.35 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/ 10.59 GFLOPS | Progress: (4/20) | 5.91 s
[Task 3/25] Current/Best: 15.57/ 16.81 GFLOPS | Progress: (8/20) | 7.85 s
[Task 3/25] Current/Best: 14.90/ 16.81 GFLOPS | Progress: (12/20) | 9.60 s
[Task 3/25] Current/Best: 7.17/ 23.74 GFLOPS | Progress: (16/20) | 11.54 s
[Task 3/25] Current/Best: 12.65/ 23.74 GFLOPS | Progress: (20/20) | 16.04 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.45/ 20.48 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.77/ 20.48 GFLOPS | Progress: (8/20) | 6.77 s
[Task 4/25] Current/Best: 21.50/ 21.50 GFLOPS | Progress: (12/20) | 11.33 s
[Task 4/25] Current/Best: 17.30/ 21.50 GFLOPS | Progress: (16/20) | 13.55 s
[Task 4/25] Current/Best: 13.31/ 21.50 GFLOPS | Progress: (20/20) | 15.43 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.32/ 10.04 GFLOPS | Progress: (4/20) | 2.64 s
[Task 5/25] Current/Best: 11.68/ 11.68 GFLOPS | Progress: (8/20) | 4.75 s
[Task 5/25] Current/Best: 11.32/ 18.05 GFLOPS | Progress: (12/20) | 7.69 s
[Task 5/25] Current/Best: 11.64/ 22.50 GFLOPS | Progress: (16/20) | 9.11 s
[Task 5/25] Current/Best: 12.01/ 22.50 GFLOPS | Progress: (20/20) | 10.99 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.18/ 20.66 GFLOPS | Progress: (4/20) | 4.05 s
[Task 6/25] Current/Best: 18.99/ 20.66 GFLOPS | Progress: (8/20) | 5.83 s
[Task 6/25] Current/Best: 13.28/ 20.66 GFLOPS | Progress: (12/20) | 7.76 s
[Task 6/25] Current/Best: 20.01/ 20.66 GFLOPS | Progress: (16/20) | 10.00 s
[Task 6/25] Current/Best: 3.75/ 20.66 GFLOPS | Progress: (20/20) | 12.55 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.28/ 12.13 GFLOPS | Progress: (4/20) | 3.60 s
[Task 7/25] Current/Best: 20.06/ 21.24 GFLOPS | Progress: (8/20) | 5.11 s
[Task 7/25] Current/Best: 14.60/ 21.24 GFLOPS | Progress: (12/20) | 7.05 s
[Task 7/25] Current/Best: 12.25/ 21.24 GFLOPS | Progress: (16/20) | 9.11 s
[Task 7/25] Current/Best: 6.31/ 21.87 GFLOPS | Progress: (20/20) | 11.55 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.82/ 13.78 GFLOPS | Progress: (4/20) | 2.88 s
[Task 8/25] Current/Best: 9.48/ 13.78 GFLOPS | Progress: (8/20) | 7.56 s
[Task 8/25] Current/Best: 12.54/ 13.78 GFLOPS | Progress: (12/20) | 13.58 s
[Task 8/25] Current/Best: 18.55/ 18.55 GFLOPS | Progress: (16/20) | 15.68 s
[Task 8/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (20/20) | 22.11 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.28/ 15.92 GFLOPS | Progress: (4/20) | 11.94 s
[Task 9/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 13.66 s
[Task 9/25] Current/Best: 8.04/ 23.46 GFLOPS | Progress: (12/20) | 16.00 s
[Task 9/25] Current/Best: 17.85/ 23.46 GFLOPS | Progress: (16/20) | 18.55 s
[Task 9/25] Current/Best: 9.25/ 23.46 GFLOPS | Progress: (20/20) | 26.16 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (4/20) | 2.60 s
[Task 10/25] Current/Best: 15.48/ 18.18 GFLOPS | Progress: (8/20) | 4.20 s
[Task 10/25] Current/Best: 13.44/ 18.85 GFLOPS | Progress: (12/20) | 5.72 s
[Task 10/25] Current/Best: 19.22/ 19.40 GFLOPS | Progress: (16/20) | 6.84 s
[Task 10/25] Current/Best: 8.84/ 19.40 GFLOPS | Progress: (20/20
) | 8.37 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.30/ 18.12 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.75/ 18.12 GFLOPS | Progress: (8/20) | 6.03 s
[Task 11/25] Current/Best: 18.11/ 18.12 GFLOPS | Progress: (12/20) | 8.10 s
[Task 11/25] Current/Best: 13.25/ 21.17 GFLOPS | Progress: (16/20) | 10.88 s
[Task 11/25] Current/Best: 19.41/ 21.63 GFLOPS | Progress: (20/20) | 12.92 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/ 18.09 GFLOPS | Progress: (4/20) | 5.39 s
[Task 12/25] Current/Best: 5.18/ 18.09 GFLOPS | Progress: (8/20) | 9.10 s
[Task 12/25] Current/Best: 18.86/ 18.91 GFLOPS | Progress: (12/20) | 11.13 s
[Task 12/25] Current/Best: 15.31/ 18.91 GFLOPS | Progress: (16/20) | 13.93 s
[Task 12/25] Current/Best: 15.04/ 18.97 GFLOPS | Progress: (20/20) | 15.85 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.46/ 17.35 GFLOPS | Progress: (4/20) | 3.68 s
[Task 13/25] Current/Best: 16.06/ 20.97 GFLOPS | Progress: (8/20) | 6.13 s
[Task 13/25] Current/Best: 19.67/ 21.77 GFLOPS | Progress: (12/20) | 8.99 s
[Task 13/25] Current/Best: 12.27/ 21.77 GFLOPS | Progress: (16/20) | 12.41 s
[Task 13/25] Current/Best: 18.53/ 21.77 GFLOPS | Progress: (20/20) | 14.60 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.68/ 13.68 GFLOPS | Progress: (4/20) | 3.27 s
[Task 14/25] Current/Best: 6.07/ 13.68 GFLOPS | Progress: (8/20) | 5.43 s
[Task 14/25] Current/Best: 19.94/ 19.94 GFLOPS | Progress: (12/20) | 8.00 s
[Task 14/25] Current/Best: 16.48/ 19.94 GFLOPS | Progress: (16/20) | 9.68 s Done.
+
[Task 14/25] Current/Best: 17.18/ 19.94 GFLOPS | Progress: (20/20) | 11.41 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.09/ 17.49 GFLOPS | Progress: (4/20) | 2.85 s
[Task 15/25] Current/Best: 14.37/ 18.08 GFLOPS | Progress: (8/20) | 4.18 s
[Task 15/25] Current/Best: 10.35/ 22.11 GFLOPS | Progress: (12/20) | 6.28 s
[Task 15/25] Current/Best: 20.42/ 22.11 GFLOPS | Progress: (16/20) | 9.67 s
[Task 15/25] Current/Best: 9.71/ 22.11 GFLOPS | Progress: (20/20) | 10.69 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.13/ 20.13 GFLOPS | Progress: (4/20) | 3.13 s
[Task 16/25] Current/Best: 3.04/ 20.13 GFLOPS | Progress: (8/20) | 4.74 s
[Task 16/25] Current/Best: 19.31/ 20.13 GFLOPS | Progress: (12/20) | 5.99 s
[Task 16/25] Current/Best: 17.77/ 20.13 GFLOPS | Progress: (16/20) |
7.38 s
[Task 16/25] Current/Best: 9.86/ 22.21 GFLOPS | Progress: (20/20) | 9.52 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.93/ 18.97 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.39/ 23.32 GFLOPS | Progress: (8/20) | 7.57 s
[Task 17/25] Current/Best: 17.01/ 23.32 GFLOPS | Progress: (12/20) | 9.62 s
[Task 17/25] Current/Best: 16.43/ 23.32 GFLOPS | Progress: (16/20) | 11.74 s
[Task 17/25] Current/Best: 10.01/ 23.32 GFLOPS | Progress: (20/20) | 13.90 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.47/ 17.09 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 10.57/ 19.50 GFLOPS | Progress: (8/20) | 7.12 s
[Task 18/25] Current/Best: 19.04/ 19.50 GFLOPS | Progress: (12/20) | 9.05 s
[Task 18/25] Current/Best: 10.08/ 19.50 GFLOPS | Progress: (16/20) | 12.63 s
[Task 18/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (20/20) | 14.15 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.15/ 20.42 GFLOPS | Progress: (4/20) | 6.01 s
[Task 19/25] Current/Best: 2.60/ 20.42 GFLOPS | Progress: (8/20) | 9.28 s
[Task 19/25] Current/Best: 19.66/ 21.51 GFLOPS | Progress: (12/20) | 12.13 s
[Task 19/25] Current/Best: 14.85/ 21.51 GFLOPS | Progress: (16/20) | 14.95 s
[Task 19/25] Current/Best: 2.70/ 23.62 GFLOPS | Progress: (20/20) | 17.77 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.95/ 15.23 GFLOPS | Progress: (4/20) | 3.28 s Done.
Done.
-
[Task 20/25] Current/Best: 10.44/ 15.15 GFLOPS | Progress: (8/20) | 6.78 s
[Task 20/25] Current/Best: 2.32/ 16.51 GFLOPS | Progress: (12/20) | 10.65 s
[Task 20/25] Current/Best: 12.50/ 16.51 GFLOPS | Progress: (16/20) | 14.36 s
[Task 20/25] Current/Best: 12.42/ 22.02 GFLOPS | Progress: (20/20) | 16.47 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.73 GFLOPS | Progress: (4/20) | 3.24 s
[Task 21/25] Current/Best: 14.63/ 17.73 GFLOPS | Progress: (8/20) | 4.78 s
[Task 21/25] Current/Best: 1.61/ 17.73 GFLOPS | Progress: (12/20) | 6.92 s
[Task 21/25] Current/Best: 17.95/ 17.95 GFLOPS | Progress: (16/20) | 10.37 s
[Task 21/25] Current/Best: 4.46/ 17.95 GFLOPS | Progress: (20/20) | 17.47 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.05 GFLOPS | Progress: (4/20
) | 2.70 s
[Task 22/25] Current/Best: 9.04/ 21.88 GFLOPS | Progress: (8/20) | 4.68 s
[Task 22/25] Current/Best: 20.06/ 21.88 GFLOPS | Progress: (12/20) | 6.98 s
[Task 22/25] Current/Best: 15.27/ 21.88 GFLOPS | Progress: (16/20) | 9.01 s
[Task 22/25] Current/Best: 14.71/ 21.88 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: 17.27/ 20.33 GFLOPS | Progress: (4/20) | 3.27 s
[Task 23/25] Current/Best: 15.45/ 20.33 GFLOPS | Progress: (8/20) | 6.53 s
[Task 23/25] Current/Best: 20.79/ 21.52 GFLOPS | Progress: (12/20) | 8.33 s
[Task 23/25] Current/Best: 6.30/ 21.52 GFLOPS | Progress: (16/20) | 15.29 s
[Task 23/25] Current/Best: 7.55/ 21.52 GFLOPS | Progress: (20/20) | 19.57 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.63/ 8.63 GFLOPS | Progress: (4/20) | 11.82 s
[Task 24/25] Current/Best: 1.99/ 8.63 GFLOPS | Progress: (8/20) | 22.91 s
[Task 24/25] Current/Best: 4.46/ 8.63 GFLOPS | Progress: (12/20) | 34.48 s Done.
-
[Task 24/25] Current/Best: 7.22/ 8.74 GFLOPS | Progress: (16/20) | 39.90 s
[Task 24/25] Current/Best: 3.33/ 8.94 GFLOPS | Progress: (20/20) | 45.89 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 2.90 GFLOPS | Progress: (4/20) | 11.58 s
[Task 25/25] Current/Best: 5.73/ 7.85 GFLOPS | Progress: (8/20) | 22.88 s
[Task 25/25] Current/Best: 6.01/ 7.85 GFLOPS | Progress: (12/20) | 34.30 s
[Task 25/25] Current/Best: 5.70/ 9.03 GFLOPS | Progress: (16/20) | 36.24 s
[Task 25/25] Current/Best: 2.83/ 9.03 GFLOPS | Progress: (20/20) | 46.95 s
+
[Task 20/25] Current/Best: 9.71/ 15.23 GFLOPS | Progress: (8/20) | 6.60 s
[Task 20/25] Current/Best: 2.32/ 16.49 GFLOPS | Progress: (12/20) | 10.70 s
[Task 20/25] Current/Best: 12.41/ 16.49 GFLOPS | Progress: (16/20) | 14.37 s
[Task 20/25] Current/Best: 12.04/ 22.31 GFLOPS | Progress: (20/20) | 16.44 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.71 GFLOPS | Progress: (4/20) | 3.19 s
[Task 21/25] Current/Best: 14.52/ 17.71 GFLOPS | Progress: (8/20) | 4.72 s
[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 6.83 s
[Task 21/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (16/20) | 10.21 s
[Task 21/25] Current/Best: 4.47/ 18.07 GFLOPS | Progress: (20/20) | 17.11 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.03 GFLOPS | Progress: (4/20
) | 2.65 s
[Task 22/25] Current/Best: 8.71/ 22.06 GFLOPS | Progress: (8/20) | 4.60 s
[Task 22/25] Current/Best: 20.02/ 22.06 GFLOPS | Progress: (12/20) | 6.86 s
[Task 22/25] Current/Best: 15.56/ 22.06 GFLOPS | Progress: (16/20) | 8.92 s
[Task 22/25] Current/Best: 14.10/ 22.06 GFLOPS | Progress: (20/20) | 10.62 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.65/ 20.99 GFLOPS | Progress: (4/20) | 3.21 s
[Task 23/25] Current/Best: 14.13/ 20.99 GFLOPS | Progress: (8/20) | 6.46 s
[Task 23/25] Current/Best: 20.97/ 21.95 GFLOPS | Progress: (12/20) | 8.23 s
[Task 23/25] Current/Best: 6.44/ 21.95 GFLOPS | Progress: (16/20) | 15.18 s
[Task 23/25] Current/Best: 7.14/ 21.95 GFLOPS | Progress: (20/20) | 19.38 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.45/ 8.45 GFLOPS | Progress: (4/20) | 11.85 s
[Task 24/25] Current/Best: 3.59/ 8.45 GFLOPS | Progress: (8/20) | 23.07 s
[Task 24/25] Current/Best: 4.54/ 8.45 GFLOPS | Progress: (12/20) | 33.77 s Done.
+
[Task 24/25] Current/Best: 6.02/ 9.00 GFLOPS | Progress: (16/20) | 39.08 s
[Task 24/25] Current/Best: 3.43/ 9.05 GFLOPS | Progress: (20/20) | 44.97 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.53/ 2.70 GFLOPS | Progress: (4/20) | 11.62 s
[Task 25/25] Current/Best: 6.32/ 8.30 GFLOPS | Progress: (8/20) | 22.88 s
[Task 25/25] Current/Best: 6.17/ 8.30 GFLOPS | Progress: (12/20) | 34.32 s
[Task 25/25] Current/Best: 5.76/ 9.08 GFLOPS | Progress: (16/20) | 36.05 s
[Task 25/25] Current/Best: 2.87/ 9.76 GFLOPS | Progress: (20/20) | 46.72 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 410.310400150006, 'median': 410.095005900007, 'std': 1.2165990299313005}
- unoptimized: {'mean': 495.4871293999895, 'median': 495.59110714999406, 'std': 0.7418536908477463}
+ optimized: {'mean': 411.2829011000031, 'median': 411.0587107500123, 'std': 0.9974879694596182}
+ unoptimized: {'mean': 493.81363693999447, 'median': 493.41480750001665, 'std': 1.7404822562804898}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 18.796 seconds)
+ **Total running time of the script:** ( 10 minutes 14.618 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 b1222b7a5..798e234da 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.236e-07 secs/op
+ 1.258e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 65c0b3fe9..f2f70e439 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x23e8cba0)), stage(b, placeholder(b, 0x1c66e070)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x23a14b40)), stage(b, placeholder(b, 0x56e6c80)), 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 b16199669..f20c504d3 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
=================
-**13:13.458** total execution time for **tutorial** files:
+**13:07.787** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:18.796 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:14.618 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.058 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.606 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:58.049 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:57.136 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.269 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.143 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.929 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.917 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.700 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.695 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.507 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.513 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.143 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.153 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 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 2e766b44f..1b0156541 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,7 +301,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
+ Numpy running time: 0.000008
naive: 0.000007
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/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. "
- vector: 0.000025
+ vector: 0.000026
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.103809998625366e-06 1.0
- naive 6.6814e-06 0.9405375427119947
- parallel 6.2064e-06 0.8736720156086635
- vector 2.45735e-05 3.459200063734128
+ numpy 8.44463000248652e-06 1.0
+ naive 6.7071000000000005e-06 0.7942443893959944
+ parallel 6.0848e-06 0.7205525876454423
+ vector 2.57058e-05 3.044041005044736
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018755
+ Numpy running time: 0.017487
@@ -996,7 +996,7 @@ 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: 3.418077
+ none: 3.417957
@@ -1101,7 +1101,7 @@ 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: 0.301639
+ blocking: 0.291410
@@ -1199,7 +1199,7 @@ 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: 0.338125
+ vectorization: 0.326456
@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], []),
@@ -1275,7 +1275,7 @@ 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: 0.117969
+ loop permutation: 0.117896
@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], []),
@@ -1376,7 +1376,7 @@ 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: 0.109896
+ array packing: 0.111626
@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], []),
@@ -1471,7 +1471,7 @@ 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: 0.110577
+ block caching: 0.110674
@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], []),
@@ -1559,7 +1559,7 @@ 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: 0.144980
+ parallelization: 0.144695
@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], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4180772058000004 1.0
- blocking 0.3016386782 0.0882480587881869
- vectorization 0.3381253558 0.09892267946032596
- loop permutation 0.11796864619999999 0.0345131602059262
- array packing 0.1098956308 0.032151301501769015
- block caching 0.11057734150000001 0.03235074424660908
- parallelization 0.14498009620000002 0.042415687964563534
+ none 3.4179572921999997 1.0
+ blocking 0.2914099378 0.08525850760775051
+ vectorization 0.3264557886 0.09551195661367487
+ loop permutation 0.11789616089999999 0.03449316384644322
+ array packing 0.1116260322 0.032658697185812664
+ block caching 0.11067449919999998 0.03238030488343619
+ parallelization 0.14469530619999998 0.04233385435511557
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.058 seconds)
+ **Total running time of the script:** ( 1 minutes 0.606 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 93d3f724f..070722f61 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-f0650986ad59efdda18a53b976e63c2f5055d4b5
+1ca07438e0c42a33a734d5cec491caed58f39883
diff --git a/docs/contribute/index.html b/docs/contribute/index.html
index 4d20441cd..fc427f532 100644
--- a/docs/contribute/index.html
+++ b/docs/contribute/index.html
@@ -422,6 +422,7 @@ design choices of the internal.</p></li>
</li>
<li class="toctree-l1"><a class="reference internal" href="release_process.html">Release Process</a><ul>
<li class="toctree-l2"><a class="reference internal" href="release_process.html#prepare-the-release-notes">Prepare the Release Notes</a></li>
+<li class="toctree-l2"><a class="reference internal" href="release_process.html#prepare-the-release-candidate">Prepare the Release Candidate</a></li>
<li class="toctree-l2"><a class="reference internal" href="release_process.html#prepare-the-gpg-key">Prepare the GPG Key</a></li>
<li class="toctree-l2"><a class="reference internal" href="release_process.html#cut-a-release-candidate">Cut a Release Candidate</a></li>
<li class="toctree-l2"><a class="reference internal" href="release_process.html#upload-the-release-candidate">Upload the Release Candidate</a></li>
diff --git a/docs/contribute/release_process.html b/docs/contribute/release_process.html
index de0a6576a..6ac46261f 100644
--- a/docs/contribute/release_process.html
+++ b/docs/contribute/release_process.html
@@ -235,6 +235,7 @@
<li class="toctree-l2"><a class="reference internal" href="ci.html">Using TVM’s CI</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Release Process</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#prepare-the-release-notes">Prepare the Release Notes</a></li>
+<li class="toctree-l3"><a class="reference internal" href="#prepare-the-release-candidate">Prepare the Release Candidate</a></li>
<li class="toctree-l3"><a class="reference internal" href="#prepare-the-gpg-key">Prepare the GPG Key</a></li>
<li class="toctree-l3"><a class="reference internal" href="#cut-a-release-candidate">Cut a Release Candidate</a></li>
<li class="toctree-l3"><a class="reference internal" href="#upload-the-release-candidate">Upload the Release Candidate</a></li>
@@ -356,13 +357,14 @@
<div class="contents local topic" id="contents">
<ul class="simple">
<li><p><a class="reference internal" href="#prepare-the-release-notes" id="id2">Prepare the Release Notes</a></p></li>
-<li><p><a class="reference internal" href="#prepare-the-gpg-key" id="id3">Prepare the GPG Key</a></p></li>
-<li><p><a class="reference internal" href="#cut-a-release-candidate" id="id4">Cut a Release Candidate</a></p></li>
-<li><p><a class="reference internal" href="#upload-the-release-candidate" id="id5">Upload the Release Candidate</a></p></li>
-<li><p><a class="reference internal" href="#call-a-vote-on-the-release-candidate" id="id6">Call a Vote on the Release Candidate</a></p></li>
-<li><p><a class="reference internal" href="#post-the-release" id="id7">Post the Release</a></p></li>
-<li><p><a class="reference internal" href="#update-the-tvm-website" id="id8">Update the TVM Website</a></p></li>
-<li><p><a class="reference internal" href="#post-the-announcement" id="id9">Post the Announcement</a></p></li>
+<li><p><a class="reference internal" href="#prepare-the-release-candidate" id="id3">Prepare the Release Candidate</a></p></li>
+<li><p><a class="reference internal" href="#prepare-the-gpg-key" id="id4">Prepare the GPG Key</a></p></li>
+<li><p><a class="reference internal" href="#cut-a-release-candidate" id="id5">Cut a Release Candidate</a></p></li>
+<li><p><a class="reference internal" href="#upload-the-release-candidate" id="id6">Upload the Release Candidate</a></p></li>
+<li><p><a class="reference internal" href="#call-a-vote-on-the-release-candidate" id="id7">Call a Vote on the Release Candidate</a></p></li>
+<li><p><a class="reference internal" href="#post-the-release" id="id8">Post the Release</a></p></li>
+<li><p><a class="reference internal" href="#update-the-tvm-website" id="id9">Update the TVM Website</a></p></li>
+<li><p><a class="reference internal" href="#post-the-announcement" id="id10">Post the Announcement</a></p></li>
</ul>
</div>
<p>The release manager role in TVM means you are responsible for a few different things:</p>
@@ -393,10 +395,14 @@
<div class="section" id="prepare-the-release-notes">
<h2><a class="toc-backref" href="#id2">Prepare the Release Notes</a><a class="headerlink" href="#prepare-the-release-notes" title="Permalink to this headline">¶</a></h2>
<p>Release note contains new features, improvement, bug fixes, known issues and deprecation, etc. TVM provides <a class="reference external" href="https://discuss.tvm.ai/search?q=TVM%20Monthly%20%23Announcement">monthly dev report</a> collects developing progress each month. It could be helpful to who writes the release notes.</p>
-<p>It is recommended to open a Github issue to collect feedbacks for the release note draft before cutting the release branch.</p>
+<p>It is recommended to open a Github issue to collect feedbacks for the release note draft before cutting the release branch. See the scripts in <code class="docutils literal notranslate"><span class="pre">tests/scripts/release</span></code> for some starting points.</p>
+</div>
+<div class="section" id="prepare-the-release-candidate">
+<h2><a class="toc-backref" href="#id3">Prepare the Release Candidate</a><a class="headerlink" href="#prepare-the-release-candidate" title="Permalink to this headline">¶</a></h2>
+<p>There may be some code changes necessary to the release branch before the release. Ensure all version numbers are up to date</p>
</div>
<div class="section" id="prepare-the-gpg-key">
-<h2><a class="toc-backref" href="#id3">Prepare the GPG Key</a><a class="headerlink" href="#prepare-the-gpg-key" title="Permalink to this headline">¶</a></h2>
+<h2><a class="toc-backref" href="#id4">Prepare the GPG Key</a><a class="headerlink" href="#prepare-the-gpg-key" title="Permalink to this headline">¶</a></h2>
<p>You can skip this section if you have already uploaded your key.</p>
<p>After generating the gpg key, you need to upload your key to a public key server. Please refer to <a class="reference external" href="https://www.apache.org/dev/openpgp.html#generate-key">https://www.apache.org/dev/openpgp.html#generate-key</a> for details.</p>
<p>If you want to do the release on another machine, you can transfer your gpg key to that machine via the <code class="code docutils literal notranslate"><span class="pre">gpg</span> <span class="pre">--export</span></code> and <code class="code docutils literal notranslate"><span class="pre">gpg</span> <span class="pre">--import</span></code> commands.</p>
@@ -406,17 +412,18 @@ svn co --depth<span class="o">=</span>files <span class="s2">"https://dist.
<span class="nb">cd</span> svn-tvm
<span class="c1"># edit KEYS file</span>
svn ci --username <span class="nv">$ASF_USERNAME</span> --password <span class="s2">"</span><span class="nv">$ASF_PASSWORD</span><span class="s2">"</span> -m <span class="s2">"Update KEYS"</span>
-<span class="c1"># update downloads.apache.org</span>
+<span class="c1"># update downloads.apache.org (note that only PMC members can update the dist/release directory)</span>
svn rm --username <span class="nv">$ASF_USERNAME</span> --password <span class="s2">"</span><span class="nv">$ASF_PASSWORD</span><span class="s2">"</span> https://dist.apache.org/repos/dist/release/tvm/KEYS -m <span class="s2">"Update KEYS"</span>
svn cp --username <span class="nv">$ASF_USERNAME</span> --password <span class="s2">"</span><span class="nv">$ASF_PASSWORD</span><span class="s2">"</span> https://dist.apache.org/repos/dist/dev/tvm/KEYS https://dist.apache.org/repos/dist/release/tvm/ -m <span class="s2">"Update KEYS"</span>
</pre></div>
</div>
</div>
<div class="section" id="cut-a-release-candidate">
-<h2><a class="toc-backref" href="#id4">Cut a Release Candidate</a><a class="headerlink" href="#cut-a-release-candidate" title="Permalink to this headline">¶</a></h2>
+<h2><a class="toc-backref" href="#id5">Cut a Release Candidate</a><a class="headerlink" href="#cut-a-release-candidate" title="Permalink to this headline">¶</a></h2>
<p>To cut a release candidate, one needs to first cut a branch using selected version string, e.g.,</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>git clone https://github.com/apache/tvm.git
<span class="nb">cd</span> tvm/
+<span class="c1"># Replace v0.6.0 with the relevant version</span>
git branch v0.6.0
git push --set-upstream origin v0.6.0
</pre></div>
@@ -436,8 +443,9 @@ git push --set-upstream origin v0.6.0
</pre></div>
</div>
<p>Create source code artifacts,</p>
-<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>git clone git@github.com:apache/tvm.git apache-tvm-src-v0.6.0.rc0
-<span class="nb">cd</span> apache-tvm-src-v0.6.0.rc0
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Replace v0.6.0 with the relevant version</span>
+git clone git@github.com:apache/tvm.git apache-tvm-src-v0.6.0
+<span class="nb">cd</span> apache-tvm-src-v0.6.0
git checkout v0.6
git submodule update --init --recursive
git checkout v0.6.0.rc0
@@ -445,7 +453,7 @@ rm -rf .DS_Store
find . -name <span class="s2">".git*"</span> -print0 <span class="p">|</span> xargs -0 rm -rf
<span class="nb">cd</span> ..
brew install gnu-tar
-gtar -czvf apache-tvm-src-v0.6.0.rc0.tar.gz apache-tvm-src-v0.6.0.rc0
+gtar -czvf apache-tvm-src-v0.6.0.rc0.tar.gz apache-tvm-src-v0.6.0
</pre></div>
</div>
<p>Use your GPG key to sign the created artifact. First make sure your GPG is set to use the correct private key,</p>
@@ -460,7 +468,7 @@ shasum -a <span class="m">512</span> apache-tvm-src-v0.6.0.rc0.tar.gz > apach
</div>
</div>
<div class="section" id="upload-the-release-candidate">
-<h2><a class="toc-backref" href="#id5">Upload the Release Candidate</a><a class="headerlink" href="#upload-the-release-candidate" title="Permalink to this headline">¶</a></h2>
+<h2><a class="toc-backref" href="#id6">Upload the Release Candidate</a><a class="headerlink" href="#upload-the-release-candidate" title="Permalink to this headline">¶</a></h2>
<p>Edit the release page on Github and upload the artifacts created by the previous steps.</p>
<p>The release manager also needs to upload the artifacts to ASF SVN,</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># the --depth=files will avoid checkout existing folders</span>
@@ -474,7 +482,7 @@ svn ci --username <span class="nv">$ASF_USERNAME</span> --password <span class="
</div>
</div>
<div class="section" id="call-a-vote-on-the-release-candidate">
-<h2><a class="toc-backref" href="#id6">Call a Vote on the Release Candidate</a><a class="headerlink" href="#call-a-vote-on-the-release-candidate" title="Permalink to this headline">¶</a></h2>
+<h2><a class="toc-backref" href="#id7">Call a Vote on the Release Candidate</a><a class="headerlink" href="#call-a-vote-on-the-release-candidate" title="Permalink to this headline">¶</a></h2>
<p>The first voting takes place on the Apache TVM developers list (<a class="reference external" href="mailto:dev%40tvm.apache.org">dev<span>@</span>tvm<span>.</span>apache<span>.</span>org</a>). To get more attention, one can create a github issue start with “[VOTE]” instead, it will be mirrored to dev@ automatically. Look at past voting threads to see how this proceeds. The email should follow this format.</p>
<ul class="simple">
<li><p>Provide the link to the draft of the release notes in the email</p></li>
@@ -486,7 +494,7 @@ svn ci --username <span class="nv">$ASF_USERNAME</span> --password <span class="
<p>If the voting fails, the community needs to modified the release accordingly, create a new release candidate and re-run the voting process.</p>
</div>
<div class="section" id="post-the-release">
-<h2><a class="toc-backref" href="#id7">Post the Release</a><a class="headerlink" href="#post-the-release" title="Permalink to this headline">¶</a></h2>
+<h2><a class="toc-backref" href="#id8">Post the Release</a><a class="headerlink" href="#post-the-release" title="Permalink to this headline">¶</a></h2>
<p>After the vote passes, to upload the binaries to Apache mirrors, you move the binaries from dev directory (this should be where they are voted) to release directory. This “moving” is the only way you can add stuff to the actual release directory. (Note: only PMC can move to release directory)</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">export</span> <span class="nv">SVN_EDITOR</span><span class="o">=</span>vim
svn mkdir https://dist.apache.org/repos/dist/release/tvm
@@ -506,11 +514,32 @@ curl <span class="s2">"https://dist.apache.org/repos/dist/dev/tvm/KEYS"
</div></blockquote>
</div>
<div class="section" id="update-the-tvm-website">
-<h2><a class="toc-backref" href="#id8">Update the TVM Website</a><a class="headerlink" href="#update-the-tvm-website" title="Permalink to this headline">¶</a></h2>
-<p>The website repository is located at <a class="reference external" href="https://github.com/apache/tvm-site">https://github.com/apache/tvm-site</a>. Modify the download page to include the release artifacts as well as the GPG signature and SHA hash.</p>
+<h2><a class="toc-backref" href="#id9">Update the TVM Website</a><a class="headerlink" href="#update-the-tvm-website" title="Permalink to this headline">¶</a></h2>
+<p>The website repository is located at <a class="reference external" href="https://github.com/apache/tvm-site">https://github.com/apache/tvm-site</a>. Modify the download page to include the release artifacts as well as the GPG signature and SHA hash. Since TVM’s docs are continually updated, upload a fixed version of the release docs. If CI has deleted the docs from the release by the time you go to update the website, you can restart the CI build for the release branch on Jenkins. See [...]
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>git clone https://github.com/apache/tvm-site.git
+<span class="nb">pushd</span> tvm-site
+git checkout asf-site
+<span class="nb">pushd</span> docs
+
+<span class="c1"># make release docs directory</span>
+mkdir v0.9.0
+<span class="nb">pushd</span> v0.9.0
+
+<span class="c1"># download the release docs from CI</span>
+<span class="c1"># find this URL by inspecting the CI logs for the most recent build of the release branch</span>
+curl -LO https://tvm-jenkins-artifacts-prod.s3.us-west-2.amazonaws.com/tvm/v0.9.0/1/docs/docs.tgz
+tar xf docs.tgz
+rm docs.tgz
+
+<span class="c1"># add the docs and push</span>
+git add .
+git commit -m<span class="s2">"Add v0.9.0 docs"</span>
+git push
+</pre></div>
+</div>
</div>
<div class="section" id="post-the-announcement">
-<h2><a class="toc-backref" href="#id9">Post the Announcement</a><a class="headerlink" href="#post-the-announcement" title="Permalink to this headline">¶</a></h2>
+<h2><a class="toc-backref" href="#id10">Post the Announcement</a><a class="headerlink" href="#post-the-announcement" title="Permalink to this headline">¶</a></h2>
<p>Send out an announcement email to <a class="reference external" href="mailto:announce%40apache.org">announce<span>@</span>apache<span>.</span>org</a>, and <a class="reference external" href="mailto:dev%40tvm.apache.org">dev<span>@</span>tvm<span>.</span>apache<span>.</span>org</a>. The announcement should include the link to release note and download page.</p>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 7a1c56744..13c521564 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.696 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.629 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.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_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index a856a7c8f..d5fffb1f5 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ 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.zip45a02494-9a29-4649-97c1-bd31de6fc96e 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.zipd607a7e7-9988-4aea-969c-4497b4227772 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 6ba892424..d8cc45e4e 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +432,14 @@ 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]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 50.7MB/s]
- 27%|##6 | 11.2M/41.5M [00:00<00:01, 27.3MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:01, 26.2MB/s]
- 45%|####5 | 18.8M/41.5M [00:00<00:00, 31.9MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 31.9MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 43.1MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 44.4MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 37.8MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 44.5MB/s]
+ 25%|##5 | 10.6M/41.5M [00:00<00:00, 41.4MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 39.0MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 44.8MB/s]
+ 64%|######4 | 26.7M/41.5M [00:00<00:00, 39.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.4MB/s]
+ 96%|#########5| 39.7M/41.5M [00:01<00:00, 41.9MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 40.0MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 03fb60726..ae645cfe9 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,10 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 10%|# | 4.57M/44.7M [00:00<00:00, 47.8MB/s]
- 20%|## | 9.13M/44.7M [00:00<00:00, 46.4MB/s]
- 69%|######8 | 30.6M/44.7M [00:00<00:00, 127MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 130MB/s]
+ 41%|####1 | 18.4M/44.7M [00:00<00:00, 193MB/s]
+ 87%|########7 | 38.9M/44.7M [00:00<00:00, 206MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 210MB/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 68070c091..35379084c 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ 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 16.230 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.528 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 f08fdb72f..398ed3669 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>05:26.251</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:12.806</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><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>01:16.230</p></td>
+<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>01:05.629</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><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>01:07.696</p></td>
+<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>01:05.528</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:40.243</p></td>
+<td><p>00:39.222</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>00:28.884</p></td>
+<tr class="row-even"><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>00:28.215</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<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>00:25.673</p></td>
+<tr class="row-odd"><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>00:27.652</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>00:25.401</p></td>
+<td><p>00:25.458</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>00:24.708</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>00:24.202</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:19.940</p></td>
+<td><p>00:19.423</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>00:15.019</p></td>
+<td><p>00:15.066</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>00:02.457</p></td>
+<td><p>00:02.411</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 1874400f1..661e7005a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2673 16.1593 17.0296 15.8406 0.3933
+ 16.3079 15.8600 20.0648 15.7761 1.2564
</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 2c9aa175b..f792129e0 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,15 +436,15 @@ 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]
- 10%|# | 17.7M/170M [00:00<00:00, 186MB/s]
- 25%|##4 | 41.8M/170M [00:00<00:00, 225MB/s]
- 39%|###8 | 65.6M/170M [00:00<00:00, 236MB/s]
- 52%|#####1 | 88.0M/170M [00:00<00:00, 232MB/s]
- 66%|######6 | 112M/170M [00:00<00:00, 239MB/s]
- 80%|#######9 | 135M/170M [00:00<00:00, 168MB/s]
- 90%|######### | 154M/170M [00:01<00:00, 108MB/s]
- 99%|#########8| 168M/170M [00:01<00:00, 96.6MB/s]
-100%|##########| 170M/170M [00:01<00:00, 138MB/s]
+ 2%|1 | 3.34M/170M [00:00<00:04, 34.9MB/s]
+ 5%|4 | 7.77M/170M [00:00<00:04, 41.7MB/s]
+ 16%|#6 | 27.8M/170M [00:00<00:01, 118MB/s]
+ 30%|##9 | 50.9M/170M [00:00<00:00, 167MB/s]
+ 44%|####3 | 74.6M/170M [00:00<00:00, 197MB/s]
+ 58%|#####7 | 97.8M/170M [00:00<00:00, 212MB/s]
+ 72%|#######1 | 122M/170M [00:00<00:00, 225MB/s]
+ 87%|########7 | 148M/170M [00:00<00:00, 241MB/s]
+100%|##########| 170M/170M [00:00<00:00, 201MB/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').
@@ -539,7 +539,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.419 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 59.581 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 feddd4c6d..91d056d83 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 160MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 177MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +569,7 @@ 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)
- 90.4510 90.3276 94.6396 90.1403 0.4694
+ 90.3224 90.2395 95.7022 90.0782 0.5620
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ 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 10.305 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.631 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 7be9dfa0a..70bfde92d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ 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)
- 119.9869 119.9461 121.5897 119.1387 0.4557
+ 120.8555 120.0777 126.9296 118.9443 1.5509
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ 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 52.303 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 55.391 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 557b75ce5..fde62f202 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.819 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 37.237 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 8ca2a55ec..4521c9f8f 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,26 +441,24 @@ 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]
- 4%|4 | 5330/132723 [00:00<00:02, 52960.64KB/s]
- 10%|9 | 12875/132723 [00:00<00:01, 66151.29KB/s]
- 15%|#4 | 19494/132723 [00:00<00:02, 56166.07KB/s]
- 20%|## | 27062/132723 [00:00<00:01, 63108.88KB/s]
- 26%|##6 | 34659/132723 [00:00<00:01, 67341.71KB/s]
- 31%|###1 | 41529/132723 [00:00<00:01, 65260.05KB/s]
- 37%|###6 | 48589/132723 [00:00<00:01, 66907.09KB/s]
- 42%|####1 | 55354/132723 [00:00<00:01, 50716.19KB/s]
- 47%|####7 | 62961/132723 [00:01<00:01, 57008.74KB/s]
- 52%|#####2 | 69228/132723 [00:01<00:01, 49574.23KB/s]
- 58%|#####7 | 76763/132723 [00:01<00:01, 55777.07KB/s]
- 62%|######2 | 82871/132723 [00:01<00:00, 56106.27KB/s]
- 68%|######8 | 90319/132723 [00:01<00:00, 60958.46KB/s]
- 74%|#######3 | 98029/132723 [00:01<00:00, 65378.89KB/s]
- 79%|#######8 | 104844/132723 [00:01<00:00, 56813.78KB/s]
- 85%|########4 | 112450/132723 [00:01<00:00, 61749.52KB/s]
- 90%|########9 | 118973/132723 [00:02<00:00, 41586.33KB/s]
- 94%|#########3| 124213/132723 [00:02<00:00, 42666.87KB/s]
- 99%|#########9| 131804/132723 [00:02<00:00, 49982.13KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 55122.45KB/s]
+ 3%|2 | 3960/132723 [00:00<00:03, 39168.78KB/s]
+ 9%|8 | 11483/132723 [00:00<00:02, 60276.99KB/s]
+ 13%|#3 | 17521/132723 [00:00<00:02, 56717.87KB/s]
+ 19%|#9 | 25800/132723 [00:00<00:01, 66611.02KB/s]
+ 26%|##5 | 34048/132723 [00:00<00:01, 72187.59KB/s]
+ 32%|###1 | 42292/132723 [00:00<00:01, 75613.34KB/s]
+ 38%|###8 | 50596/132723 [00:00<00:01, 78011.57KB/s]
+ 44%|####4 | 58800/132723 [00:00<00:00, 79282.19KB/s]
+ 51%|##### | 67079/132723 [00:00<00:00, 80366.26KB/s]
+ 57%|#####6 | 75352/132723 [00:01<00:00, 81091.19KB/s]
+ 63%|######3 | 83670/132723 [00:01<00:00, 81727.02KB/s]
+ 69%|######9 | 91977/132723 [00:01<00:00, 82132.04KB/s]
+ 75%|#######5 | 100196/132723 [00:01<00:00, 59734.12KB/s]
+ 82%|########1 | 108481/132723 [00:01<00:00, 65260.20KB/s]
+ 87%|########7 | 115758/132723 [00:01<00:00, 61216.51KB/s]
+ 93%|#########3| 123957/132723 [00:01<00:00, 66386.29KB/s]
+100%|#########9| 132373/132723 [00:01<00:00, 71046.39KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 70445.75KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -503,7 +501,7 @@ 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 36.163 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 35.378 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 514372ea1..a7e6c14ac 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>11:40.120</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:30.764</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</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>03:02.419</p></td>
+<td><p>02:59.581</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>02:36.163</p></td>
+<td><p>02:35.378</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>01:52.303</p></td>
+<td><p>01:55.391</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>01:43.819</p></td>
+<td><p>01:37.237</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>01:10.305</p></td>
+<td><p>01:09.631</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>00:30.243</p></td>
+<td><p>00:29.759</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.625</p></td>
+<td><p>00:22.219</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:22.237</p></td>
+<td><p>00:21.562</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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 1eb22f8a1..fa40d7a60 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ 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.zipc1b7ff4e-769a-43e6-b403-876f4d0c3d27 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.zip54806edd-ebeb-4204-9236-3f733f76ad76 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 6066c1368..f177c2bcf 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:41.124</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.012</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</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>00:37.924</p></td>
+<td><p>00:36.946</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>00:02.225</p></td>
+<td><p>00:02.147</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>00:00.967</p></td>
+<td><p>00:00.912</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>00:00.008</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 c5f695642..06e912293 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ 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: 6530us [6530us] (45.79%; 45.79%)
-FoldScaleAxis: 7731us [6us] (54.21%; 54.21%)
- FoldConstant: 7726us [1595us] (54.17%; 99.93%)
- InferType: 6131us [6131us] (42.99%; 79.35%)
+InferType: 6516us [6516us] (45.89%; 45.89%)
+FoldScaleAxis: 7683us [5us] (54.11%; 54.11%)
+ FoldConstant: 7677us [1587us] (54.07%; 99.93%)
+ InferType: 6090us [6090us] (42.89%; 79.33%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ 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: 6128us [6128us] (44.61%; 44.61%)
-FoldScaleAxis: 7609us [5us] (55.39%; 55.39%)
- FoldConstant: 7605us [1567us] (55.36%; 99.94%)
- InferType: 6038us [6038us] (43.95%; 79.39%)
+InferType: 6131us [6131us] (44.52%; 44.52%)
+FoldScaleAxis: 7641us [5us] (55.48%; 55.48%)
+ FoldConstant: 7637us [1595us] (55.45%; 99.94%)
+ InferType: 6041us [6041us] (43.87%; 79.11%)
</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 359ac293a..f963a61dd 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ 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: 50.269086 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.203462 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 f3544c061..f53a835ed 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ 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: 10.024940 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.833399 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 aca547cac..1088f8a0e 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ 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: 0.019196
-Baseline: 3.299340
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018883
+Baseline: 3.428025
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ 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: 0.319600
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.316967
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ 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: 0.348555
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.338233
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ 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: 0.119710
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117703
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ 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: 0.110977
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111367
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ 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: 0.111555
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112490
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ 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: 0.145087
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145839
</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 2ee4f6e3a..808dda74b 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:34.635</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.851</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</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>00:32.342</p></td>
+<td><p>00:32.548</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>00:01.239</p></td>
+<td><p>00:01.246</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>00:01.053</p></td>
+<td><p>00:01.057</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 129b7d95f..4c3189d26 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>06:09.810</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:54.339</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</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>03:22.207</p></td>
+<td><p>03:12.135</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>01:22.650</p></td>
+<td><p>01:21.658</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>00:46.311</p></td>
+<td><p>00:45.015</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>00:20.707</p></td>
+<td><p>00:18.143</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>00:09.003</p></td>
+<td><p>00:08.705</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>00:08.932</p></td>
+<td><p>00:08.683</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 6159611cd..ead34571e 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
@@ -491,777 +491,192 @@ 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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 32) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*784)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*144)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 56), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 168), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 280), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else(((((1 <= (floordiv(threadIdx.x_1, 9) + ry.outer.outer)) && ((floordiv(threadIdx.x_1, 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 384)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 616), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 728), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 840), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 952), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 48)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 504), 48)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 48), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 40), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 48)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((threadIdx.x_1 < 48) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 30), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 30), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 8), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = 0f32
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 112), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 168), 144)*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 336), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 504), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 728), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 840), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (rc.inner: int32, 0, 8) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*648) + (rc.inner*81)) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (rc.inner*9)) + 8)]))
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 384)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 385)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 386)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 387)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 388)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 389)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 390)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 391)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 392)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 393)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 394)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 395)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 396)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 397)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 398)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 399)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 400)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 401)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 402)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 403)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 404)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 405)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 406)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 407)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 408)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 409)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 410)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 411)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 412)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 413)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 720)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 720)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 721)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 721)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 722)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 722)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 675)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 675)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 676)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 676)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 677)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 677)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 684)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 684)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 414)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 685)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 685)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 415)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 686)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 416)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 417)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 418)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 419)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 783)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 783)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 784)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 785)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 785)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 846)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 846)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 847)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 847)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 848)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 848)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 792)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 792)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 793)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 793)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 794)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 794)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 855)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 855)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 856)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 856)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 857)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 857)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 801)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 801)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 802)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 802)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 803)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 803)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 864)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 864)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 865)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 865)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 866)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 866)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 420)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 421)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 422)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 873)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 873)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 423)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 874)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 874)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 424)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 875)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 875)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 425)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 918)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 918)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 919)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 919)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 920)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 920)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 927)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 927)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 928)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 928)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 929)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 929)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 936)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 936)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 426)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 937)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 937)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 427)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 938)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 938)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 428)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 999)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 999)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 429)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1000)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1000)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 430)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1001)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1001)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 431)]))
}
}
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 392)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
- }
+ compute[((blockIdx.x*392) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
</pre></div>
@@ -1297,7 +712,7 @@ 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: 0.415 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.189 ms
</pre></div>
</div>
</div>
@@ -1329,18 +744,18 @@ conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nch
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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=8)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, 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=1)
+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=7)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
@@ -1350,13 +765,13 @@ 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_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
-compute_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_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1382,7 +797,7 @@ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fus
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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", 1024)
+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, "unroll_explicit", True)
CUDA source code:
@@ -1401,739 +816,143 @@ CUDA source code:
#define uint64_t unsigned long long
#endif
extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[768];
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = (((((1 <= ((((int)threadIdx.x) / 9) + ry_outer_outer)) && (((((int)threadIdx.x) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((1 <= (((((int)threadIdx.x) + 7) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) + 7) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) % 48) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- if (((int)threadIdx.x) < 40) {
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + (((((int)threadIdx.x) + 24) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((4 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + (((((int)threadIdx.x) + 5) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + (((((int)threadIdx.x) + 11) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 8) {
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = 0.000000e+00f;
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 648) + (rc_inner * 81)) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (rc_inner * 9)) + 8)]));
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 384)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 385)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 386)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 387)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 388)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 389)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 390)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 391)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 392)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 393)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 394)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 395)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 396)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 397)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 398)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 399)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 400)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 401)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 402)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 403)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 404)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 405)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 406)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 407)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 408)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 409)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 410)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 411)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 412)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 413)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 720)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 720)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 721)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 721)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 722)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 722)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 666)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 666)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 729)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 729)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 675)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 675)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 676)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 676)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 677)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 677)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 738)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 738)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 684)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 684)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 414)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 685)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 685)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 415)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 686)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 686)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 416)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 747)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 747)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 417)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 418)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 419)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 783)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 783)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 784)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 784)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 785)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 785)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 846)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 846)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 847)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 847)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 848)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 848)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 792)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 792)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 793)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 793)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 794)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 794)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 855)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 855)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 856)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 856)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 857)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 857)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 801)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 801)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 802)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 802)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 803)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 803)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 864)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 864)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 865)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 865)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 866)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 866)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 810)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 810)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 420)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 421)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 422)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 873)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 873)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 423)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 874)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 874)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 424)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 875)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 875)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 425)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 918)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 918)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 919)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 919)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 920)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 920)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 981)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 981)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 927)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 927)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 928)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 928)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 929)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 929)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 990)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 990)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 936)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 936)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 426)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 937)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 937)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 427)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 938)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 938)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 428)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 999)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 999)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 429)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1000)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1000)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 430)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1001)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1001)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 431)]));
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
- }
+ compute[((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -2169,7 +988,7 @@ 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> ( 3 minutes 22.207 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 12.135 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 aaab8dd0a..beda449d5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ 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)
- 9.8633 9.8669 9.8715 9.8516 0.0085
+ 9.7879 9.7805 9.8337 9.7494 0.0348
</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 17ab4c873..24e94563a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ 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)
- 766.8072 766.7924 766.9597 766.6695 0.1189
+ 753.6852 753.3992 754.7367 752.9197 0.7689
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ 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 22.650 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.658 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 9d5d53484..ed86a7ae0 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,12 +625,12 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), 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, 32) "parallel" {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = ((i.outer.inner*1024) + (i.inner.init*16))
+ for (i.outer.inner: int32, 0, 16) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.outer.inner*128) + (i.inner.init*16))
{
compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
@@ -650,78 +650,52 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 64) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_2: int32 = ((i.outer.inner*1024) + (i.inner*16))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_4: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*1024) + (i.inner*16)) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*16384) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
+ let cse_var_18: int32 = ((i.outer.inner*128) + (i.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_18: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute[ramp(cse_var_18, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_18, 1, 16)]), broadcast(0f32, 16))
+ let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
+ let cse_var_22: int32 = ((i0.inner*512) + cse_var_23)
+ compute[ramp(cse_var_22, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_23) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -759,7 +733,7 @@ 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: 1.833 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.610 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 903cd1e80..61b8daf6e 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:46.202</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.570</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,7 +336,7 @@
</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>00:46.166</p></td>
+<td><p>00:45.535</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>
@@ -344,7 +344,7 @@
<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>
-<td><p>00:00.006</p></td>
+<td><p>00:00.005</p></td>
<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>
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 dba37d169..ea07fcb08 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 192.42/192.42 result: MeasureResult(costs=(0.0012030982222222223,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0964510440826416, timestamp=1659479230.9060364) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/192.42 result: Traceback (most recent call last):
+No: 9 GFLOPS: 80.85/80.85 result: MeasureResult(costs=(0.002863335142857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8809525966644287, timestamp=1659484687.395197) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/80.85 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
@@ -1560,8 +1560,8 @@ 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, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.47/260.47 result: MeasureResult(costs=(0.0008887805083798882,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4137368202209473, timestamp=1659479231.8076637) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.10/260.10 result: MeasureResult(costs=(0.0008900587900552485,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7123539447784424, timestamp=1659484688.2929778) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.10 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
@@ -1684,7 +1684,7 @@ 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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.10 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
@@ -1807,7 +1807,7 @@ 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, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.10 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
@@ -1930,9 +1930,9 @@ 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, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.29/260.47 result: MeasureResult(costs=(0.04377225825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.842933177947998, timestamp=1659479236.371284) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.36/260.47 result: MeasureResult(costs=(0.06892603624999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.579137086868286, timestamp=1659479237.6056433) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.46/260.10 result: MeasureResult(costs=(0.042374166500000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8468067646026611, timestamp=1659484692.840606) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/260.10 result: MeasureResult(costs=(0.0693154735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.531064510345459, timestamp=1659484694.0785117) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.10 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
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.00/260.47 result: MeasureResult(costs=(0.008268678357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2928235530853271, timestamp=1659479248.6388752) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.01/260.10 result: MeasureResult(costs=(0.008265518142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3182411193847656, timestamp=1659484705.1653576) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.10 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
@@ -2074,7 +2074,7 @@ 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, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.47 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.10 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
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001322
+Time cost of this operator: 0.001220
</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 a43f0108c..79baf0d86 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.4 98.731 (1, 2, 10, 10, 3) 2 1 [313.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.054 0.962 (1, 6, 10, 10) 1 1 [3.054]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.307 (1, 1, 10, 10, 3) 1 1 [0.974]
-Total_time - 317.428 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.8 98.693 (1, 2, 10, 10, 3) 2 1 [309.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.147 1.003 (1, 6, 10, 10) 1 1 [3.147]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.305 (1, 1, 10, 10, 3) 1 1 [0.956]
+Total_time - 313.903 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 219.9 98.635 (1, 1, 10, 10, 6) 2 1 [219.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.2 0.987 (1, 6, 10, 10) 1 1 [2.2]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.378 (1, 3, 10, 10, 1) 1 1 [0.843]
-Total_time - 222.943 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.438 96.676 (1, 6, 10, 10, 1) 2 1 [80.438]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.792 2.153 (1, 6, 10, 10) 1 1 [1.792]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 1.171 (1, 1, 10, 10, 3) 1 1 [0.974]
+Total_time - 83.203 - - - - -
</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 2681b3d4f..ea1e7a704 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ 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/tmpijas024t/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmphy0jj1fy/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ 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/tmpijas024t/images/target contains 8144 images
-/tmp/tmpijas024t/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/tmphy0jj1fy/images/target contains 8144 images
+/tmp/tmphy0jj1fy/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ 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 - 56s - loss: 0.2151 - accuracy: 0.9280 - val_loss: 0.1213 - val_accuracy: 0.9615
+328/328 - 56s - loss: 0.2103 - accuracy: 0.9276 - val_loss: 0.1370 - val_accuracy: 0.9562
Epoch 2/3
-328/328 - 53s - loss: 0.1029 - accuracy: 0.9623 - val_loss: 0.1111 - val_accuracy: 0.9626
+328/328 - 52s - loss: 0.0977 - accuracy: 0.9636 - val_loss: 0.1129 - val_accuracy: 0.9641
Epoch 3/3
-328/328 - 52s - loss: 0.0685 - accuracy: 0.9750 - val_loss: 0.1541 - val_accuracy: 0.9505
+328/328 - 52s - loss: 0.0685 - accuracy: 0.9738 - val_loss: 0.1673 - val_accuracy: 0.9377
-<keras.callbacks.History object at 0x7efef1110b90>
+<keras.callbacks.History object at 0x7f82503de210>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ 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> ( 5 minutes 28.119 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 33.153 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 fa285c6a1..d5b0a757a 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>06:21.916</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:25.683</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</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>05:28.119</p></td>
+<td><p>05:33.153</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>00:42.617</p></td>
+<td><p>00:41.655</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.852</p></td>
+<td><p>00:07.634</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:03.326</p></td>
+<td><p>00:03.240</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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 2e7d037b2..3c794a051 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:42.151</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.922</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.822</p></td>
+<td><p>00:30.727</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:09.812</p></td>
+<td><p>00:09.958</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:01.509</p></td>
+<td><p>00:02.230</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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 ff86d9f0f..ff384bee4 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ 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 0x7efe76945e60>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f81b3d785f0>
</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 7fadfa8c5..dec010b2b 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:04.107</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.127</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,23 +336,23 @@
</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>00:01.896</p></td>
+<td><p>00:01.908</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>00:00.976</p></td>
+<td><p>00:00.978</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>00:00.533</p></td>
+<td><p>00:00.541</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>00:00.515</p></td>
+<td><p>00:00.516</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>00:00.103</p></td>
+<td><p>00:00.102</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>
@@ -360,7 +360,7 @@
<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>00:00.028</p></td>
+<td><p>00:00.027</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 9ea5afe55..d891677f9 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ 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/tmp_73auzf3/input0.cc'\nsource_filename = \"/tmp/tmp_73auzf3/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/tmps095mswj/input0.cc'\nsource_filename = \"/tmp/tmps095mswj/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/install/nnpack.html b/docs/install/nnpack.html
index aa2238b85..3153785d7 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,17 +224,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 217a799b1..79c89e934 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ 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>
@@ -1886,7 +1886,7 @@ 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 757178559..42991a2dd 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/f0650986a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 25977e327..1c6f1348a 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/f0650986a/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 873a967b6..863a9bcc4 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/f0650986a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 55cbb9aa6..7fbfb56e4 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/f0650986a/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 dd1b08a69..d43fda94f 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/f0650986a/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 b3603ac11..ad651f0b1 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/f0650986a/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 a39a68e01..e33adbb1d 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/f0650986a/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 ced32e140..09015ffe7 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/f0650986a/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/web/src/runtime.ts#L1140">runtime.ts:1140</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/f0650986a/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 fd26645fd..c2870216a 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/f0650986a/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 ff42fd816..948e57fdc 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/f0650986a/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 129d9ddcb..a158ca11c 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/f0650986a/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 c44ee015c..32f982ecf 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/f0650986a/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 caf82f13a..f5a8b78f7 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/f0650986a/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 3f7f212fa..81d208cab 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/f0650986a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 aab8c7e5a..c94437106 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/f0650986a/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 be683f273..4140c2b7f 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/f0650986a/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 7ca230101..29240bc24 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/f0650986a/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 b87a0bca5..0ce35f44a 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/f0650986a/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 70216c8e1..e1124c7e3 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/f0650986a/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 be5495670..43bb985c4 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/f0650986a/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 e328bec17..2b2683b0a 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/f0650986a/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/web/src/runtime.ts#L1362">runtime.ts:1362</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/f0650986a/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 c3765e0fa..f3b9794cd 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/f0650986a/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 5701c4abf..ae2779430 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/f0650986a/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 054cb6b8c..6f354dc7f 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/f0650986a/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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/f0650986a/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1ca07438e/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 b6a048595..e2d74a233 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 c4cf45c5c..ef0a531d0 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:21.797</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.734</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</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>00:21.791</p></td>
+<td><p>00:21.727</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 b085761c2..7b131976e 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ 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 23.54s!
+resnet18_v1 inference graph built in 23.45s!
</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 85a7e8bc4..4e569961f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ 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 16.55s!
+yolov3-tiny inference graph built in 16.13s!
</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 eaa822427..43dd0bae1 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>01:33.195</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:33.917</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</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>00:49.504</p></td>
+<td><p>00:50.274</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>00:43.692</p></td>
+<td><p>00:43.642</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 c7ee26d6e..da7ab0702 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:03.293</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.255</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</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>00:02.900</p></td>
+<td><p>00:02.848</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>00:00.393</p></td>
+<td><p>00:00.407</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 5770e2408..86116e2ab 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:00.700</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.716</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</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>00:00.374</p></td>
+<td><p>00:00.380</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>00:00.326</p></td>
+<td><p>00:00.336</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 cc13caec4..0ec616ffa 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -566,7 +566,7 @@ 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: 93.208 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.031 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index be981890c..0e36ae4d3 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -668,16 +668,16 @@ 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: 8.88/8.88 result: MeasureResult(costs=(0.0302405864,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6165728569030762, timestamp=1659477976.4120898) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.94/8.88 result: MeasureResult(costs=(0.0914235504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6181211471557617, timestamp=1659477978.56386) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.0227730018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6103503704071045, timestamp=1659477979.1305115) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.87/11.79 result: MeasureResult(costs=(0.14388056200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.428006410598755, timestamp=1659477982.1260848) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.65/11.79 result: MeasureResult(costs=(0.07363607,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.319868564605713, timestamp=1659477983.5741856) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.76/11.79 result: MeasureResult(costs=(0.1524592394,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6105194091796875, timestamp=1659477986.7659535) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.79 result: MeasureResult(costs=(0.307379643,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.035019159317017, timestamp=1659477991.8476741) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.25/11.79 result: MeasureResult(costs=(0.026182003600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5667905807495117, timestamp=1659477992.4284546) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.89/11.79 result: MeasureResult(costs=(0.1420826808,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3733842372894287, timestamp=1659477994.9220536) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.49/11.79 result: MeasureResult(costs=(0.1079180346,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8324904441833496, timestamp=1659477996.8122902) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.53/10.53 result: MeasureResult(costs=(0.0255032078,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5398743152618408, timestamp=1659483456.5337129) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.92/10.53 result: MeasureResult(costs=(0.0919450734,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6158719062805176, timestamp=1659483458.6942506) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.0227363286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6014094352722168, timestamp=1659483459.2596972) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.85/11.81 result: MeasureResult(costs=(0.1451020456,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.441189765930176, timestamp=1659483462.270703) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.67/11.81 result: MeasureResult(costs=(0.0731474764,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3007020950317383, timestamp=1659483463.7008047) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.77/11.81 result: MeasureResult(costs=(0.1513506104,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5422887802124023, timestamp=1659483466.8076324) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.81 result: MeasureResult(costs=(0.308321106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.055330514907837, timestamp=1659483471.9059725) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 9.78/11.81 result: MeasureResult(costs=(0.0274402584,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5829212665557861, timestamp=1659483472.5071592) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.69/11.81 result: MeasureResult(costs=(0.15905891879999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.64192795753479, timestamp=1659483475.268641) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.76/11.81 result: MeasureResult(costs=(0.09741225299999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6625261306762695, timestamp=1659483476.989076) [('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 5ba7d417e..201a50ea9 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -550,7 +550,7 @@ 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': 495.4871293999895, 'median': 495.59110714999406, 'std': 0.7418536908477463}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.81363693999447, 'median': 493.41480750001665, 'std': 1.7404822562804898}
</pre></div>
</div>
</div>
@@ -705,178 +705,178 @@ 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: 17.55/ 17.55 GFLOPS | Progress: (4/20) | 6.34 s
-[Task 1/25] Current/Best: 6.16/ 17.55 GFLOPS | Progress: (8/20) | 9.35 s
-[Task 1/25] Current/Best: 11.48/ 22.77 GFLOPS | Progress: (12/20) | 11.78 s
-[Task 1/25] Current/Best: 16.82/ 22.82 GFLOPS | Progress: (16/20) | 13.46 s
-[Task 1/25] Current/Best: 11.62/ 23.81 GFLOPS | Progress: (20/20) | 15.20 s Done.
+[Task 1/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 6.29 s
+[Task 1/25] Current/Best: 6.16/ 17.53 GFLOPS | Progress: (8/20) | 9.32 s
+[Task 1/25] Current/Best: 11.51/ 22.74 GFLOPS | Progress: (12/20) | 11.75 s
+[Task 1/25] Current/Best: 16.72/ 22.84 GFLOPS | Progress: (16/20) | 13.44 s
+[Task 1/25] Current/Best: 11.58/ 23.68 GFLOPS | Progress: (20/20) | 15.17 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.24/ 13.06 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 2/25] Current/Best: 13.93/ 18.30 GFLOPS | Progress: (8/20) | 4.96 s
-[Task 2/25] Current/Best: 20.89/ 20.89 GFLOPS | Progress: (12/20) | 6.27 s
-[Task 2/25] Current/Best: 12.71/ 20.89 GFLOPS | Progress: (16/20) | 7.52 s
-[Task 2/25] Current/Best: 19.96/ 20.89 GFLOPS | Progress: (20/20) | 9.08 s Done.
+[Task 2/25] Current/Best: 12.32/ 13.14 GFLOPS | Progress: (4/20) | 3.83 s
+[Task 2/25] Current/Best: 13.76/ 17.74 GFLOPS | Progress: (8/20) | 5.16 s
+[Task 2/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (12/20) | 6.52 s
+[Task 2/25] Current/Best: 12.51/ 21.35 GFLOPS | Progress: (16/20) | 7.79 s
+[Task 2/25] Current/Best: 17.77/ 21.35 GFLOPS | Progress: (20/20) | 9.35 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/ 10.50 GFLOPS | Progress: (4/20) | 5.88 s
-[Task 3/25] Current/Best: 15.54/ 16.86 GFLOPS | Progress: (8/20) | 7.81 s
-[Task 3/25] Current/Best: 14.87/ 16.86 GFLOPS | Progress: (12/20) | 9.57 s
-[Task 3/25] Current/Best: 7.21/ 23.73 GFLOPS | Progress: (16/20) | 11.49 s
-[Task 3/25] Current/Best: 11.97/ 23.73 GFLOPS | Progress: (20/20) | 16.01 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.59 GFLOPS | Progress: (4/20) | 5.91 s
+[Task 3/25] Current/Best: 15.57/ 16.81 GFLOPS | Progress: (8/20) | 7.85 s
+[Task 3/25] Current/Best: 14.90/ 16.81 GFLOPS | Progress: (12/20) | 9.60 s
+[Task 3/25] Current/Best: 7.17/ 23.74 GFLOPS | Progress: (16/20) | 11.54 s
+[Task 3/25] Current/Best: 12.65/ 23.74 GFLOPS | Progress: (20/20) | 16.04 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.39/ 20.15 GFLOPS | Progress: (4/20) | 2.42 s
-[Task 4/25] Current/Best: 6.87/ 20.15 GFLOPS | Progress: (8/20) | 6.74 s
-[Task 4/25] Current/Best: 22.14/ 22.14 GFLOPS | Progress: (12/20) | 11.20 s
-[Task 4/25] Current/Best: 17.40/ 22.14 GFLOPS | Progress: (16/20) | 13.40 s
-[Task 4/25] Current/Best: 13.47/ 22.14 GFLOPS | Progress: (20/20) | 15.37 s Done.
+[Task 4/25] Current/Best: 9.45/ 20.48 GFLOPS | Progress: (4/20) | 2.39 s
+[Task 4/25] Current/Best: 6.77/ 20.48 GFLOPS | Progress: (8/20) | 6.77 s
+[Task 4/25] Current/Best: 21.50/ 21.50 GFLOPS | Progress: (12/20) | 11.33 s
+[Task 4/25] Current/Best: 17.30/ 21.50 GFLOPS | Progress: (16/20) | 13.55 s
+[Task 4/25] Current/Best: 13.31/ 21.50 GFLOPS | Progress: (20/20) | 15.43 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.62/ 10.46 GFLOPS | Progress: (4/20) | 2.62 s
-[Task 5/25] Current/Best: 11.75/ 13.19 GFLOPS | Progress: (8/20) | 4.69 s
-[Task 5/25] Current/Best: 10.97/ 17.72 GFLOPS | Progress: (12/20) | 7.78 s
-[Task 5/25] Current/Best: 11.84/ 22.47 GFLOPS | Progress: (16/20) | 9.24 s
-[Task 5/25] Current/Best: 11.93/ 22.47 GFLOPS | Progress: (20/20) | 11.10 s Done.
+[Task 5/25] Current/Best: 9.32/ 10.04 GFLOPS | Progress: (4/20) | 2.64 s
+[Task 5/25] Current/Best: 11.68/ 11.68 GFLOPS | Progress: (8/20) | 4.75 s
+[Task 5/25] Current/Best: 11.32/ 18.05 GFLOPS | Progress: (12/20) | 7.69 s
+[Task 5/25] Current/Best: 11.64/ 22.50 GFLOPS | Progress: (16/20) | 9.11 s
+[Task 5/25] Current/Best: 12.01/ 22.50 GFLOPS | Progress: (20/20) | 10.99 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.23/ 20.79 GFLOPS | Progress: (4/20) | 3.96 s
-[Task 6/25] Current/Best: 19.01/ 20.79 GFLOPS | Progress: (8/20) | 5.71 s
-[Task 6/25] Current/Best: 13.22/ 20.79 GFLOPS | Progress: (12/20) | 7.62 s
-[Task 6/25] Current/Best: 20.01/ 20.79 GFLOPS | Progress: (16/20) | 9.86 s
-[Task 6/25] Current/Best: 3.73/ 20.79 GFLOPS | Progress: (20/20) | 12.41 s Done.
+[Task 6/25] Current/Best: 12.18/ 20.66 GFLOPS | Progress: (4/20) | 4.05 s
+[Task 6/25] Current/Best: 18.99/ 20.66 GFLOPS | Progress: (8/20) | 5.83 s
+[Task 6/25] Current/Best: 13.28/ 20.66 GFLOPS | Progress: (12/20) | 7.76 s
+[Task 6/25] Current/Best: 20.01/ 20.66 GFLOPS | Progress: (16/20) | 10.00 s
+[Task 6/25] Current/Best: 3.75/ 20.66 GFLOPS | Progress: (20/20) | 12.55 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.19/ 12.37 GFLOPS | Progress: (4/20) | 3.59 s
-[Task 7/25] Current/Best: 20.26/ 21.01 GFLOPS | Progress: (8/20) | 5.12 s
-[Task 7/25] Current/Best: 15.89/ 21.01 GFLOPS | Progress: (12/20) | 7.06 s
-[Task 7/25] Current/Best: 12.22/ 21.01 GFLOPS | Progress: (16/20) | 9.11 s
-[Task 7/25] Current/Best: 6.36/ 21.68 GFLOPS | Progress: (20/20) | 11.59 s Done.
+[Task 7/25] Current/Best: 11.28/ 12.13 GFLOPS | Progress: (4/20) | 3.60 s
+[Task 7/25] Current/Best: 20.06/ 21.24 GFLOPS | Progress: (8/20) | 5.11 s
+[Task 7/25] Current/Best: 14.60/ 21.24 GFLOPS | Progress: (12/20) | 7.05 s
+[Task 7/25] Current/Best: 12.25/ 21.24 GFLOPS | Progress: (16/20) | 9.11 s
+[Task 7/25] Current/Best: 6.31/ 21.87 GFLOPS | Progress: (20/20) | 11.55 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.26/ 13.84 GFLOPS | Progress: (4/20) | 2.96 s
-[Task 8/25] Current/Best: 9.67/ 13.84 GFLOPS | Progress: (8/20) | 7.66 s
-[Task 8/25] Current/Best: 12.93/ 13.84 GFLOPS | Progress: (12/20) | 13.78 s
-[Task 8/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (16/20) | 15.85 s
-[Task 8/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (20/20) | 22.34 s Done.
+[Task 8/25] Current/Best: 9.82/ 13.78 GFLOPS | Progress: (4/20) | 2.88 s
+[Task 8/25] Current/Best: 9.48/ 13.78 GFLOPS | Progress: (8/20) | 7.56 s
+[Task 8/25] Current/Best: 12.54/ 13.78 GFLOPS | Progress: (12/20) | 13.58 s
+[Task 8/25] Current/Best: 18.55/ 18.55 GFLOPS | Progress: (16/20) | 15.68 s
+[Task 8/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (20/20) | 22.11 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.38/ 15.55 GFLOPS | Progress: (4/20) | 11.95 s
-[Task 9/25] Current/Best: 23.35/ 23.35 GFLOPS | Progress: (8/20) | 13.74 s
-[Task 9/25] Current/Best: 8.26/ 23.35 GFLOPS | Progress: (12/20) | 16.11 s
-[Task 9/25] Current/Best: 18.04/ 23.35 GFLOPS | Progress: (16/20) | 18.75 s
-[Task 9/25] Current/Best: 9.08/ 23.35 GFLOPS | Progress: (20/20) | 26.53 s
+[Task 9/25] Current/Best: 14.28/ 15.92 GFLOPS | Progress: (4/20) | 11.94 s
+[Task 9/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 13.66 s
+[Task 9/25] Current/Best: 8.04/ 23.46 GFLOPS | Progress: (12/20) | 16.00 s
+[Task 9/25] Current/Best: 17.85/ 23.46 GFLOPS | Progress: (16/20) | 18.55 s
+[Task 9/25] Current/Best: 9.25/ 23.46 GFLOPS | Progress: (20/20) | 26.16 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 10/25] Current/Best: 15.54/ 18.21 GFLOPS | Progress: (8/20) | 4.22 s
-[Task 10/25] Current/Best: 12.62/ 18.87 GFLOPS | Progress: (12/20) | 5.75 s
-[Task 10/25] Current/Best: 19.13/ 20.41 GFLOPS | Progress: (16/20) | 6.86 s
-[Task 10/25] Current/Best: 8.82/ 20.41 GFLOPS | Progress: (20/20) | 8.39 s Done.
+[Task 10/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (4/20) | 2.60 s
+[Task 10/25] Current/Best: 15.48/ 18.18 GFLOPS | Progress: (8/20) | 4.20 s
+[Task 10/25] Current/Best: 13.44/ 18.85 GFLOPS | Progress: (12/20) | 5.72 s
+[Task 10/25] Current/Best: 19.22/ 19.40 GFLOPS | Progress: (16/20) | 6.84 s
+[Task 10/25] Current/Best: 8.84/ 19.40 GFLOPS | Progress: (20/20) | 8.37 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.23/ 18.14 GFLOPS | Progress: (4/20) | 3.35 s
-[Task 11/25] Current/Best: 16.43/ 18.14 GFLOPS | Progress: (8/20) | 6.08 s
-[Task 11/25] Current/Best: 17.22/ 18.14 GFLOPS | Progress: (12/20) | 8.12 s
-[Task 11/25] Current/Best: 13.47/ 21.18 GFLOPS | Progress: (16/20) | 10.91 s
-[Task 11/25] Current/Best: 19.36/ 21.54 GFLOPS | Progress: (20/20) | 12.92 s Done.
+[Task 11/25] Current/Best: 12.30/ 18.12 GFLOPS | Progress: (4/20) | 3.32 s
+[Task 11/25] Current/Best: 16.75/ 18.12 GFLOPS | Progress: (8/20) | 6.03 s
+[Task 11/25] Current/Best: 18.11/ 18.12 GFLOPS | Progress: (12/20) | 8.10 s
+[Task 11/25] Current/Best: 13.25/ 21.17 GFLOPS | Progress: (16/20) | 10.88 s
+[Task 11/25] Current/Best: 19.41/ 21.63 GFLOPS | Progress: (20/20) | 12.92 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.73/ 18.00 GFLOPS | Progress: (4/20) | 5.40 s
-[Task 12/25] Current/Best: 5.20/ 18.00 GFLOPS | Progress: (8/20) | 9.12 s
-[Task 12/25] Current/Best: 18.64/ 19.10 GFLOPS | Progress: (12/20) | 11.13 s
-[Task 12/25] Current/Best: 15.04/ 19.10 GFLOPS | Progress: (16/20) | 13.92 s
-[Task 12/25] Current/Best: 15.11/ 19.10 GFLOPS | Progress: (20/20) | 15.87 s Done.
+[Task 12/25] Current/Best: 7.80/ 18.09 GFLOPS | Progress: (4/20) | 5.39 s
+[Task 12/25] Current/Best: 5.18/ 18.09 GFLOPS | Progress: (8/20) | 9.10 s
+[Task 12/25] Current/Best: 18.86/ 18.91 GFLOPS | Progress: (12/20) | 11.13 s
+[Task 12/25] Current/Best: 15.31/ 18.91 GFLOPS | Progress: (16/20) | 13.93 s
+[Task 12/25] Current/Best: 15.04/ 18.97 GFLOPS | Progress: (20/20) | 15.85 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.20/ 17.24 GFLOPS | Progress: (4/20) | 3.71 s
-[Task 13/25] Current/Best: 15.59/ 20.74 GFLOPS | Progress: (8/20) | 6.16 s
-[Task 13/25] Current/Best: 19.67/ 21.41 GFLOPS | Progress: (12/20) | 9.04 s
-[Task 13/25] Current/Best: 12.21/ 21.41 GFLOPS | Progress: (16/20) | 12.41 s
-[Task 13/25] Current/Best: 18.22/ 21.41 GFLOPS | Progress: (20/20) | 14.63 s Done.
+[Task 13/25] Current/Best: 8.46/ 17.35 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 13/25] Current/Best: 16.06/ 20.97 GFLOPS | Progress: (8/20) | 6.13 s
+[Task 13/25] Current/Best: 19.67/ 21.77 GFLOPS | Progress: (12/20) | 8.99 s
+[Task 13/25] Current/Best: 12.27/ 21.77 GFLOPS | Progress: (16/20) | 12.41 s
+[Task 13/25] Current/Best: 18.53/ 21.77 GFLOPS | Progress: (20/20) | 14.60 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.68/ 13.68 GFLOPS | Progress: (4/20) | 3.37 s
-[Task 14/25] Current/Best: 6.12/ 13.68 GFLOPS | Progress: (8/20) | 5.53 s
-[Task 14/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (12/20) | 8.05 s
-[Task 14/25] Current/Best: 16.29/ 20.58 GFLOPS | Progress: (16/20) | 9.71 s Done.
+[Task 14/25] Current/Best: 13.68/ 13.68 GFLOPS | Progress: (4/20) | 3.27 s
+[Task 14/25] Current/Best: 6.07/ 13.68 GFLOPS | Progress: (8/20) | 5.43 s
+[Task 14/25] Current/Best: 19.94/ 19.94 GFLOPS | Progress: (12/20) | 8.00 s
+[Task 14/25] Current/Best: 16.48/ 19.94 GFLOPS | Progress: (16/20) | 9.68 s Done.
-[Task 14/25] Current/Best: 16.72/ 20.58 GFLOPS | Progress: (20/20) | 11.46 s
+[Task 14/25] Current/Best: 17.18/ 19.94 GFLOPS | Progress: (20/20) | 11.41 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.17/ 17.68 GFLOPS | Progress: (4/20) | 2.73 s
-[Task 15/25] Current/Best: 14.26/ 18.05 GFLOPS | Progress: (8/20) | 4.06 s
-[Task 15/25] Current/Best: 10.35/ 22.35 GFLOPS | Progress: (12/20) | 6.13 s
-[Task 15/25] Current/Best: 20.39/ 22.35 GFLOPS | Progress: (16/20) | 9.61 s
-[Task 15/25] Current/Best: 9.67/ 22.35 GFLOPS | Progress: (20/20) | 10.63 s
+[Task 15/25] Current/Best: 16.09/ 17.49 GFLOPS | Progress: (4/20) | 2.85 s
+[Task 15/25] Current/Best: 14.37/ 18.08 GFLOPS | Progress: (8/20) | 4.18 s
+[Task 15/25] Current/Best: 10.35/ 22.11 GFLOPS | Progress: (12/20) | 6.28 s
+[Task 15/25] Current/Best: 20.42/ 22.11 GFLOPS | Progress: (16/20) | 9.67 s
+[Task 15/25] Current/Best: 9.71/ 22.11 GFLOPS | Progress: (20/20) | 10.69 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (4/20) | 2.99 s
-[Task 16/25] Current/Best: 3.04/ 20.55 GFLOPS | Progress: (8/20) | 4.62 s
-[Task 16/25] Current/Best: 19.11/ 20.55 GFLOPS | Progress: (12/20) | 5.84 s
-[Task 16/25] Current/Best: 18.13/ 20.55 GFLOPS | Progress: (16/20) | 7.18 s
-[Task 16/25] Current/Best: 9.94/ 22.16 GFLOPS | Progress: (20/20) | 9.24 s Done.
+[Task 16/25] Current/Best: 20.13/ 20.13 GFLOPS | Progress: (4/20) | 3.13 s
+[Task 16/25] Current/Best: 3.04/ 20.13 GFLOPS | Progress: (8/20) | 4.74 s
+[Task 16/25] Current/Best: 19.31/ 20.13 GFLOPS | Progress: (12/20) | 5.99 s
+[Task 16/25] Current/Best: 17.77/ 20.13 GFLOPS | Progress: (16/20) | 7.38 s
+[Task 16/25] Current/Best: 9.86/ 22.21 GFLOPS | Progress: (20/20) | 9.52 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.65/ 18.60 GFLOPS | Progress: (4/20) | 4.75 s
-[Task 17/25] Current/Best: 14.40/ 23.05 GFLOPS | Progress: (8/20) | 7.52 s
-[Task 17/25] Current/Best: 16.74/ 23.05 GFLOPS | Progress: (12/20) | 9.57 s
-[Task 17/25] Current/Best: 17.45/ 23.05 GFLOPS | Progress: (16/20) | 11.69 s
-[Task 17/25] Current/Best: 10.01/ 23.05 GFLOPS | Progress: (20/20) | 13.84 s Done.
+[Task 17/25] Current/Best: 13.93/ 18.97 GFLOPS | Progress: (4/20) | 4.72 s
+[Task 17/25] Current/Best: 14.39/ 23.32 GFLOPS | Progress: (8/20) | 7.57 s
+[Task 17/25] Current/Best: 17.01/ 23.32 GFLOPS | Progress: (12/20) | 9.62 s
+[Task 17/25] Current/Best: 16.43/ 23.32 GFLOPS | Progress: (16/20) | 11.74 s
+[Task 17/25] Current/Best: 10.01/ 23.32 GFLOPS | Progress: (20/20) | 13.90 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.41/ 18.09 GFLOPS | Progress: (4/20) | 3.71 s
-[Task 18/25] Current/Best: 10.52/ 19.00 GFLOPS | Progress: (8/20) | 7.14 s
-[Task 18/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (12/20) | 9.06 s
-[Task 18/25] Current/Best: 9.96/ 19.15 GFLOPS | Progress: (16/20) | 12.60 s
-[Task 18/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (20/20) | 14.12 s Done.
+[Task 18/25] Current/Best: 11.47/ 17.09 GFLOPS | Progress: (4/20) | 3.71 s
+[Task 18/25] Current/Best: 10.57/ 19.50 GFLOPS | Progress: (8/20) | 7.12 s
+[Task 18/25] Current/Best: 19.04/ 19.50 GFLOPS | Progress: (12/20) | 9.05 s
+[Task 18/25] Current/Best: 10.08/ 19.50 GFLOPS | Progress: (16/20) | 12.63 s
+[Task 18/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (20/20) | 14.15 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.09/ 20.30 GFLOPS | Progress: (4/20) | 6.04 s
-[Task 19/25] Current/Best: 2.61/ 20.30 GFLOPS | Progress: (8/20) | 9.28 s
-[Task 19/25] Current/Best: 19.47/ 21.45 GFLOPS | Progress: (12/20) | 12.12 s
-[Task 19/25] Current/Best: 15.31/ 21.45 GFLOPS | Progress: (16/20) | 14.90 s
-[Task 19/25] Current/Best: 2.70/ 23.38 GFLOPS | Progress: (20/20) | 17.68 s Done.
+[Task 19/25] Current/Best: 7.15/ 20.42 GFLOPS | Progress: (4/20) | 6.01 s
+[Task 19/25] Current/Best: 2.60/ 20.42 GFLOPS | Progress: (8/20) | 9.28 s
+[Task 19/25] Current/Best: 19.66/ 21.51 GFLOPS | Progress: (12/20) | 12.13 s
+[Task 19/25] Current/Best: 14.85/ 21.51 GFLOPS | Progress: (16/20) | 14.95 s
+[Task 19/25] Current/Best: 2.70/ 23.62 GFLOPS | Progress: (20/20) | 17.77 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.87/ 15.15 GFLOPS | Progress: (4/20) | 3.35 s Done.
+[Task 20/25] Current/Best: 8.95/ 15.23 GFLOPS | Progress: (4/20) | 3.28 s Done.
Done.
-[Task 20/25] Current/Best: 10.44/ 15.15 GFLOPS | Progress: (8/20) | 6.78 s
-[Task 20/25] Current/Best: 2.32/ 16.51 GFLOPS | Progress: (12/20) | 10.65 s
-[Task 20/25] Current/Best: 12.50/ 16.51 GFLOPS | Progress: (16/20) | 14.36 s
-[Task 20/25] Current/Best: 12.42/ 22.02 GFLOPS | Progress: (20/20) | 16.47 s
+[Task 20/25] Current/Best: 9.71/ 15.23 GFLOPS | Progress: (8/20) | 6.60 s
+[Task 20/25] Current/Best: 2.32/ 16.49 GFLOPS | Progress: (12/20) | 10.70 s
+[Task 20/25] Current/Best: 12.41/ 16.49 GFLOPS | Progress: (16/20) | 14.37 s
+[Task 20/25] Current/Best: 12.04/ 22.31 GFLOPS | Progress: (20/20) | 16.44 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.40/ 17.73 GFLOPS | Progress: (4/20) | 3.24 s
-[Task 21/25] Current/Best: 14.63/ 17.73 GFLOPS | Progress: (8/20) | 4.78 s
-[Task 21/25] Current/Best: 1.61/ 17.73 GFLOPS | Progress: (12/20) | 6.92 s
-[Task 21/25] Current/Best: 17.95/ 17.95 GFLOPS | Progress: (16/20) | 10.37 s
-[Task 21/25] Current/Best: 4.46/ 17.95 GFLOPS | Progress: (20/20) | 17.47 s
+[Task 21/25] Current/Best: 6.42/ 17.71 GFLOPS | Progress: (4/20) | 3.19 s
+[Task 21/25] Current/Best: 14.52/ 17.71 GFLOPS | Progress: (8/20) | 4.72 s
+[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 6.83 s
+[Task 21/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (16/20) | 10.21 s
+[Task 21/25] Current/Best: 4.47/ 18.07 GFLOPS | Progress: (20/20) | 17.11 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 17.05 GFLOPS | Progress: (4/20) | 2.70 s
-[Task 22/25] Current/Best: 9.04/ 21.88 GFLOPS | Progress: (8/20) | 4.68 s
-[Task 22/25] Current/Best: 20.06/ 21.88 GFLOPS | Progress: (12/20) | 6.98 s
-[Task 22/25] Current/Best: 15.27/ 21.88 GFLOPS | Progress: (16/20) | 9.01 s
-[Task 22/25] Current/Best: 14.71/ 21.88 GFLOPS | Progress: (20/20) | 10.73 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.03 GFLOPS | Progress: (4/20) | 2.65 s
+[Task 22/25] Current/Best: 8.71/ 22.06 GFLOPS | Progress: (8/20) | 4.60 s
+[Task 22/25] Current/Best: 20.02/ 22.06 GFLOPS | Progress: (12/20) | 6.86 s
+[Task 22/25] Current/Best: 15.56/ 22.06 GFLOPS | Progress: (16/20) | 8.92 s
+[Task 22/25] Current/Best: 14.10/ 22.06 GFLOPS | Progress: (20/20) | 10.62 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.27/ 20.33 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 23/25] Current/Best: 15.45/ 20.33 GFLOPS | Progress: (8/20) | 6.53 s
-[Task 23/25] Current/Best: 20.79/ 21.52 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 23/25] Current/Best: 6.30/ 21.52 GFLOPS | Progress: (16/20) | 15.29 s
-[Task 23/25] Current/Best: 7.55/ 21.52 GFLOPS | Progress: (20/20) | 19.57 s Done.
+[Task 23/25] Current/Best: 17.65/ 20.99 GFLOPS | Progress: (4/20) | 3.21 s
+[Task 23/25] Current/Best: 14.13/ 20.99 GFLOPS | Progress: (8/20) | 6.46 s
+[Task 23/25] Current/Best: 20.97/ 21.95 GFLOPS | Progress: (12/20) | 8.23 s
+[Task 23/25] Current/Best: 6.44/ 21.95 GFLOPS | Progress: (16/20) | 15.18 s
+[Task 23/25] Current/Best: 7.14/ 21.95 GFLOPS | Progress: (20/20) | 19.38 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.63/ 8.63 GFLOPS | Progress: (4/20) | 11.82 s
-[Task 24/25] Current/Best: 1.99/ 8.63 GFLOPS | Progress: (8/20) | 22.91 s
-[Task 24/25] Current/Best: 4.46/ 8.63 GFLOPS | Progress: (12/20) | 34.48 s Done.
+[Task 24/25] Current/Best: 8.45/ 8.45 GFLOPS | Progress: (4/20) | 11.85 s
+[Task 24/25] Current/Best: 3.59/ 8.45 GFLOPS | Progress: (8/20) | 23.07 s
+[Task 24/25] Current/Best: 4.54/ 8.45 GFLOPS | Progress: (12/20) | 33.77 s Done.
-[Task 24/25] Current/Best: 7.22/ 8.74 GFLOPS | Progress: (16/20) | 39.90 s
-[Task 24/25] Current/Best: 3.33/ 8.94 GFLOPS | Progress: (20/20) | 45.89 s Done.
+[Task 24/25] Current/Best: 6.02/ 9.00 GFLOPS | Progress: (16/20) | 39.08 s
+[Task 24/25] Current/Best: 3.43/ 9.05 GFLOPS | Progress: (20/20) | 44.97 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.54/ 2.90 GFLOPS | Progress: (4/20) | 11.58 s
-[Task 25/25] Current/Best: 5.73/ 7.85 GFLOPS | Progress: (8/20) | 22.88 s
-[Task 25/25] Current/Best: 6.01/ 7.85 GFLOPS | Progress: (12/20) | 34.30 s
-[Task 25/25] Current/Best: 5.70/ 9.03 GFLOPS | Progress: (16/20) | 36.24 s
-[Task 25/25] Current/Best: 2.83/ 9.03 GFLOPS | Progress: (20/20) | 46.95 s
+[Task 25/25] Current/Best: 1.53/ 2.70 GFLOPS | Progress: (4/20) | 11.62 s
+[Task 25/25] Current/Best: 6.32/ 8.30 GFLOPS | Progress: (8/20) | 22.88 s
+[Task 25/25] Current/Best: 6.17/ 8.30 GFLOPS | Progress: (12/20) | 34.32 s
+[Task 25/25] Current/Best: 5.76/ 9.08 GFLOPS | Progress: (16/20) | 36.05 s
+[Task 25/25] Current/Best: 2.87/ 9.76 GFLOPS | Progress: (20/20) | 46.72 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -980,8 +980,8 @@ 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': 410.310400150006, 'median': 410.095005900007, 'std': 1.2165990299313005}
-unoptimized: {'mean': 495.4871293999895, 'median': 495.59110714999406, 'std': 0.7418536908477463}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 411.2829011000031, 'median': 411.0587107500123, 'std': 0.9974879694596182}
+unoptimized: {'mean': 493.81363693999447, 'median': 493.41480750001665, 'std': 1.7404822562804898}
</pre></div>
</div>
</div>
@@ -995,7 +995,7 @@ 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 18.796 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 14.618 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 a57559df4..8c5d2e636 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -526,7 +526,7 @@ 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>1.236e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.258e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 3a4230b2f..1e49b18fd 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -483,7 +483,7 @@ 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, 0x23e8cba0)), stage(b, placeholder(b, 0x1c66e070)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x23a14b40)), stage(b, placeholder(b, 0x56e6c80)), 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 514852f2e..d914f0071 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>13:13.458</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:07.787</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,46 +336,46 @@
</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>10:18.796</p></td>
+<td><p>10:14.618</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>01:01.058</p></td>
+<td><p>01:00.606</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>00:58.049</p></td>
+<td><p>00:57.136</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>00:30.269</p></td>
+<td><p>00:30.143</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>00:23.929</p></td>
+<td><p>00:23.917</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:00.700</p></td>
+<td><p>00:00.695</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:00.507</p></td>
+<td><p>00:00.513</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>00:00.143</p></td>
+<td><p>00:00.153</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>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</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 ff24b37e7..9da8a70c5 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -541,7 +541,7 @@ helper function to run a profile of the TVM generated code.</p>
... 134 lines suppressed ...