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 2022/08/23 10:38:59 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@383bd419310fac4d9d78e0c59760cbef3efa5555)
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 acd7ec31d deploying docs (apache/tvm@383bd419310fac4d9d78e0c59760cbef3efa5555)
acd7ec31d is described below
commit acd7ec31d20960444d3873eddc1bed318e19fa86
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Aug 23 10:38:52 2022 +0000
deploying docs (apache/tvm@383bd419310fac4d9d78e0c59760cbef3efa5555)
---
docs/_sources/contribute/ci.rst.txt | 23 +
.../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 | 8 +-
.../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 | 1741 ++++++++++++++++++--
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 29 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../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 | 12 +-
.../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 | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 40 +-
docs/commit_hash | 2 +-
docs/contribute/ci.html | 38 +-
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 | 12 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 23 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
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 | 1741 ++++++++++++++++++--
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 29 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../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 | 12 +-
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 | 32 +-
docs/tutorial/tensor_expr_get_started.html | 40 +-
124 files changed, 4142 insertions(+), 1045 deletions(-)
diff --git a/docs/_sources/contribute/ci.rst.txt b/docs/_sources/contribute/ci.rst.txt
index a421103ab..1284fd95f 100644
--- a/docs/_sources/contribute/ci.rst.txt
+++ b/docs/_sources/contribute/ci.rst.txt
@@ -174,6 +174,29 @@ The images for these containers are hosted in the `tlcpack Docker Hub <https://h
and referenced in the `Jenkinsfile.j2 <https://github.com/apache/tvm/tree/main/Jenkinsfile.j2>`_. These can be inspected and run
locally via standard Docker commands.
+Adding a new Docker image
+"""""""""""""""""""""""""
+
+New docker images can be added to test TVM on a variety of platforms. Here are the steps for adding
+a new CI image:
+
+1. Define the ``docker/Dockerfile.ci_foo`` and associated scripts in ``docker/install``. Create a PR containing only these changes (no ``Jenkinsfile`` changes).
+
+ Example: https://github.com/apache/tvm/pull/12230/files
+
+2. A committer verifies the image builds locally and then reviews/approves this PR.
+3. A committer creates the ci-foo repos in https://hub.docker.com/u/tlcpack and https://hub.docker.com/u/tlcpackstaging.
+4. Create a PR to create an ECR repo for the image in tlcpack/ci: https://github.com/tlc-pack/ci/pull/46/files
+5. A committer creates and gets merged a PR to add the image to the ``Jenkinsfile``
+
+ Example: https://github.com/apache/tvm/pull/12369/files.
+
+ **NOTE**: The PR must be opened from a branch in apache/tvm, not from a branch in a forked repo.
+
+6. A committer adds this image to the daily docker rebuild/validation run in tlcpack.
+
+ Example: https://github.com/tlc-pack/tlcpack/pull/131
+
``ci-docker-staging``
^^^^^^^^^^^^^^^^^^^^^
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 30c149c01..8d2befe7a 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 2.307 seconds)
+ **Total running time of the script:** ( 1 minutes 2.543 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 077d900eb..fd71e3dd8 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.zip3b333d2c-aed8-4b57-b607-d42b4e5c6f12 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip16c13765-9594-44c2-b482-af293cb91e96 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 07942bfe3..300cda709 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]
19%|#9 | 7.99M/41.5M [00:00<00:00, 56.0MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 54.5MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 53.9MB/s]
66%|######6 | 27.5M/41.5M [00:00<00:00, 48.3MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 51.1MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 56.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 55.3MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 62.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 53.3MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 59.7MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 48.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 53.3MB/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 cbb09a086..fd7beecdd 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]
37%|###6 | 16.3M/44.7M [00:00<00:00, 171MB/s]
78%|#######8 | 34.9M/44.7M [00:00<00:00, 185MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 153MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
39%|###9 | 17.5M/44.7M [00:00<00:00, 184MB/s]
92%|#########1| 40.9M/44.7M [00:00<00:00, 220MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 218MB/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 32d843bf8..b043614f1 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 1.691 seconds)
+ **Total running time of the script:** ( 1 minutes 4.987 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 ab88e8842..fe325abbb 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
=================
-**04:57.387** total execution time for **how_to_compile_models** files:
+**05:05.836** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:02.307 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.987 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.691 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:02.543 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.511 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.248 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.517 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.668 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.018 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.182 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.011 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.242 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.694 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.168 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.039 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.470 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.664 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.845 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.936 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.481 | 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 c1cf6744c..9619adae8 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)
- 15.4482 15.4740 15.6752 15.2577 0.1224
+ 15.8027 15.8138 16.0244 15.6502 0.1103
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 0151943fa..35b6a4251 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]
5%|5 | 8.73M/170M [00:00<00:01, 91.5MB/s]
10%|# | 17.5M/170M [00:00<00:01, 89.6MB/s]
19%|#8 | 32.0M/170M [00:00<00:01, 118MB/s]
27%|##6 | 45.2M/170M [00:00<00:01, 126MB/s]
34%|###3 | 57.2M/170M [00:00<00:01, 114MB/s]
40%|#### | 68.3M/170M [00:00<00:00, 111MB/s]
47%|####6 | 79.0M/170M [00:00<00:00, 104MB/s]
59%|#####8 | 99.5M/170M [00:00<00:00, 136MB/s]
70%|######9 | 118M/170M [00:00<00:00, 154MB/s]
79%|#######8 | 133M/170M [00:01<00:00, 149MB/s]
87%|########7 | 148M/170M [00:01<00:00, 118MB/s]
94%|#########4| 160M/170M [00:01<00:00, 109MB/s]
100%|##########| 170M/170M [00:01<00:00, 118MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|9 | 15.9M/170M [00:00<00:00, 167MB/s]
22%|##2 | 38.2M/170M [00:00<00:00, 206MB/s]
36%|###5 | 60.8M/170M [00:00<00:00, 220MB/s]
50%|####9 | 84.4M/170M [00:00<00:00, 231MB/s]
65%|######5 | 111M/170M [00:00<00:00, 248MB/s]
81%|########1 | 138M/170M [00:00<00:00, 259MB/s]
97%|#########6| 164M/170M [00:00<00:00, 265MB/s]
100%|##########| 170M/170M [00:00<00:00, 245MB/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:** ( 2 minutes 53.986 seconds)
+ **Total running time of the script:** ( 2 minutes 54.528 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 3b7603cff..abb281f28 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, 144MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
28%|##8 | 3.80M/13.6M [00:00<00:00, 39.0MB/s]
65%|######4 | 8.78M/13.6M [00:00<00:00, 46.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 61.2MB/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)
- 89.2087 89.1286 92.8700 88.8271 0.4262
+ 90.4212 90.0720 104.3539 89.9028 1.7381
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.614 seconds)
+ **Total running time of the script:** ( 1 minutes 8.468 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 520c4f7fd..fb2683ba4 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)
- 122.8810 122.6769 131.6116 121.7623 1.1060
+ 120.7667 120.7356 123.0604 119.2780 0.5273
@@ -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 55.424 seconds)
+ **Total running time of the script:** ( 1 minutes 53.307 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 c4944df53..3810e7b6e 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 24.443 seconds)
+ **Total running time of the script:** ( 1 minutes 24.303 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 776860411..f7973dd06 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]
3%|2 | 3597/132723 [00:00<00:03, 35967.46KB/s]
9%|8 | 11362/132723 [00:00<00:02, 60483.72KB/s]
14%|#4 | 18992/132723 [00:00<00:01, 67703.25KB/s]
21%|## | 27267/132723 [00:00<00:01, 73640.06KB/s]
26%|##6 | 34631/132723 [00:00<00:01, 71254.73KB/s]
32%|###2 | 42807/132723 [00:00<00:01, 74746.31KB/s]
38%|###8 | 51054/132723 [00:00<00:01, 77232.90KB/s]
45%|####4 | 59350/132723 [00:00<00:00, 79035.05KB/s]
51%|##### | 67591/132723 [00:00<00:00, 80080.94KB/s]
57%|#####7 | 75979/132723 [00:01<00:00, 81241.04KB/s]
64%|######3 | 84321/132723 [00:01<00:00, 81903.69KB/s]
70%|######9 | 92658/132723 [00:01<00:00, 82346.32KB/s]
76%|#######6 | 101032/132723 [00:01<00:00, 82764.66KB/s]
82%|########2 | 109485/132723 [00:01<00:00, 83294.44KB/s]
89%|########8 | 117817/132723 [00:01<00:00, 83065.73KB/s]
95%|########
#5| 126131/132723 [00:01<00:00, 83085.26KB/s]
100%|##########| 132723/132723 [00:01<00:00, 78455.00KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6230/132723 [00:00<00:02, 62292.49KB/s]
11%|# | 14541/132723 [00:00<00:01, 74529.57KB/s]
17%|#7 | 23041/132723 [00:00<00:01, 79305.13KB/s]
24%|##3 | 31492/132723 [00:00<00:01, 81357.42KB/s]
30%|### | 39913/132723 [00:00<00:01, 82382.49KB/s]
36%|###6 | 48346/132723 [00:00<00:01, 83038.50KB/s]
43%|####2 | 56834/132723 [00:00<00:00, 83637.30KB/s]
49%|####9 | 65295/132723 [00:00<00:00, 83945.36KB/s]
56%|#####5 | 73849/132723 [00:00<00:00, 84440.14KB/s]
62%|######2 | 82294/132723 [00:01<00:00, 84380.18KB/s]
68%|######8 | 90733/132723 [00:01<00:00, 84267.86KB/s]
75%|#######4 | 99160/132723 [00:01<00:00, 84190.42KB/s]
81%|########1 | 107648/132723 [00:01<00:00, 84395.78KB/s]
87%|########7 | 116100/132723 [00:01<00:00, 84431.22KB/s]
94%|#########3| 124583/132723 [00:01<00:00, 84549.77KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83036.94KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 33.210 seconds)
+ **Total running time of the script:** ( 2 minutes 34.620 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 c1f7012e0..6657b1e70 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
=================
-**11:08.572** total execution time for **how_to_deploy_models** files:
+**11:08.593** 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``) | 02:53.986 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:54.528 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:33.210 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:34.620 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:55.424 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:53.307 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:24.443 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:24.303 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.614 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.468 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.460 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.632 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:21.765 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.663 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.688 | 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 58a1db645..6047e9b97 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.zip05ec726a-902c-4f2c-9818-ad5306d36f25 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip24645e29-09bb-418b-ac1e-a62aa744bfea 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 0785aa72d..6be2c583a 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
=================
-**00:41.134** total execution time for **how_to_extend_tvm** files:
+**00:41.330** 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``) | 00:37.859 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.111 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.297 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.255 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.971 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.957 | 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 |
+-------------------------------------------------------------------------------------------------+-----------+--------+
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 6d4b28a0f..9bc549723 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: 6702us [6702us] (45.54%; 45.54%)
- FoldScaleAxis: 8016us [6us] (54.46%; 54.46%)
- FoldConstant: 8010us [1684us] (54.42%; 99.93%)
- InferType: 6326us [6326us] (42.98%; 78.97%)
+ InferType: 6762us [6762us] (46.03%; 46.03%)
+ FoldScaleAxis: 7930us [5us] (53.97%; 53.97%)
+ FoldConstant: 7925us [1655us] (53.94%; 99.94%)
+ InferType: 6270us [6270us] (42.67%; 79.12%)
@@ -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: 6476us [6476us] (44.91%; 44.91%)
- FoldScaleAxis: 7946us [5us] (55.09%; 55.09%)
- FoldConstant: 7940us [1686us] (55.06%; 99.93%)
- InferType: 6254us [6254us] (43.37%; 78.77%)
+ InferType: 6308us [6308us] (44.13%; 44.13%)
+ FoldScaleAxis: 7986us [4us] (55.87%; 55.87%)
+ FoldConstant: 7982us [1638us] (55.84%; 99.94%)
+ InferType: 6344us [6344us] (44.38%; 79.48%)
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 e46f89b79..44f43a05e 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: 48.074004 ms
+ Convolution: 54.227265 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 7dd8781b1..51056d9ae 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: 10.387367 ms
+ conv2d with tensor core: 6.538848 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 f15bca617..9a2a887b7 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: 0.018712
- Baseline: 3.396784
+ Numpy running time: 0.019083
+ Baseline: 3.306953
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.300497
+ Opt1: 0.296575
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.333640
+ Opt2: 0.328893
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.115574
+ Opt3: 0.115053
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109513
+ Opt4: 0.111465
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.109566
+ Opt5: 0.110850
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.145610
+ Opt6: 0.146783
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 772c25343..5758ff668 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
=================
-**00:34.391** total execution time for **how_to_optimize_operators** files:
+**00:34.152** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.139 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.878 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.254 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.226 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.998 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.049 | 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 b5bd0f022..52b8dc76a 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
=================
-**06:01.728** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:12.439** 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``) | 03:14.918 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:26.775 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.922 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.267 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.794 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:20.916 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.189 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.736 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.838 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.640 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.577 | 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 ffd7d588b..adffc9b1e 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
@@ -240,75 +240,959 @@ 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;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ 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[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 256) {
- let cse_var_1: int32 = (rc.outer.outer*18)
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[(threadIdx.x_1*9)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*9) + 1)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 2)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 3)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 5)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 4)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 4)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 5)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 3)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 6)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 2)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 7)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 1)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 8)] = 0f32
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 6), 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 18))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 18)*4608)) + cse_var_1) + threadIdx.x_2) + 10)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 10), 27)) && (floormod((threadIdx.x_1 + 10), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 20), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + ((floordiv(threadIdx.x_1, 3) + 1)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 192), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 384), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 768), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 960), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1536), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1920), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2112), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2496), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3072), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3200), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3264), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3328), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3520), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3648), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3712), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3776), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3968), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4096), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4160), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4224), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4288), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4416), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4544), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4608)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4672)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4672), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4736)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4736), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4800)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4800), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4864)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4864), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4928), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4992)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4992), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5056)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5056), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5120)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5184)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5248)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5248), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5312)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5312), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5376), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5440)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5440), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5504)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5504), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5568)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5568), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5632)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5632), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5696)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5696), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5760)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5824), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5888)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5888), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5952)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5952), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6016)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6016), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6080)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6080), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6144)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6144), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6208)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6208), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6272), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6336)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6400)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6400), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6464)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6528)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6528), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6592)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6592), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6656)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6656), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6720)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6720), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6784)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6848)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6848), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6912)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6976)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6976), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7040)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7040), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7104)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7104), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7168), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7232)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7296)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7296), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7360)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7360), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7424)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7424), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7488)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7552)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7552), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7616)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7680)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7680), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7744)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7744), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7808)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7872)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7872), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7936)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7936), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8000)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8000), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8128)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8192)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8192), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8256)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8256), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8320)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8320), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8384)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8384), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8448)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8448), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8512)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8512), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8576)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8576), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8640)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8704)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8704), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8768)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8768), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8832)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8832), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8896)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8960), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 9024)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 9024), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 9088)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 9088), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 9152)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 9152), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (xx.outer.inner: int32, 0, 7) {
- let cse_var_2: int32 = (xx.outer.inner + 7)
- {
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 147)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 150)]))
- }
- }
+ let cse_var_110: int32 = (rc.outer.inner*108)
+ let cse_var_109: int32 = (cse_var_110 + 99)
+ let cse_var_108: int32 = (cse_var_110 + 98)
+ let cse_var_107: int32 = (cse_var_110 + 97)
+ let cse_var_106: int32 = (cse_var_110 + 96)
+ let cse_var_105: int32 = (cse_var_110 + 95)
+ let cse_var_104: int32 = (cse_var_110 + 94)
+ let cse_var_103: int32 = (cse_var_110 + 93)
+ let cse_var_102: int32 = (cse_var_110 + 92)
+ let cse_var_101: int32 = (cse_var_110 + 91)
+ let cse_var_100: int32 = (cse_var_110 + 90)
+ let cse_var_99: int32 = (cse_var_110 + 9)
+ let cse_var_98: int32 = (cse_var_110 + 89)
+ let cse_var_97: int32 = (cse_var_110 + 88)
+ let cse_var_96: int32 = (cse_var_110 + 87)
+ let cse_var_95: int32 = (cse_var_110 + 86)
+ let cse_var_94: int32 = (cse_var_110 + 85)
+ let cse_var_93: int32 = (cse_var_110 + 84)
+ let cse_var_92: int32 = (cse_var_110 + 83)
+ let cse_var_91: int32 = (cse_var_110 + 82)
+ let cse_var_90: int32 = (cse_var_110 + 81)
+ let cse_var_89: int32 = (cse_var_110 + 80)
+ let cse_var_88: int32 = (cse_var_110 + 8)
+ let cse_var_87: int32 = (cse_var_110 + 79)
+ let cse_var_86: int32 = (cse_var_110 + 78)
+ let cse_var_85: int32 = (cse_var_110 + 77)
+ let cse_var_84: int32 = (cse_var_110 + 76)
+ let cse_var_83: int32 = (cse_var_110 + 75)
+ let cse_var_82: int32 = (cse_var_110 + 74)
+ let cse_var_81: int32 = (cse_var_110 + 73)
+ let cse_var_80: int32 = (cse_var_110 + 72)
+ let cse_var_79: int32 = (cse_var_110 + 71)
+ let cse_var_78: int32 = (cse_var_110 + 70)
+ let cse_var_77: int32 = (cse_var_110 + 7)
+ let cse_var_76: int32 = (cse_var_110 + 69)
+ let cse_var_75: int32 = (cse_var_110 + 68)
+ let cse_var_74: int32 = (cse_var_110 + 67)
+ let cse_var_73: int32 = (cse_var_110 + 66)
+ let cse_var_72: int32 = (cse_var_110 + 65)
+ let cse_var_71: int32 = (cse_var_110 + 64)
+ let cse_var_70: int32 = (cse_var_110 + 63)
+ let cse_var_69: int32 = (cse_var_110 + 62)
+ let cse_var_68: int32 = (cse_var_110 + 61)
+ let cse_var_67: int32 = (cse_var_110 + 60)
+ let cse_var_66: int32 = (cse_var_110 + 6)
+ let cse_var_65: int32 = (cse_var_110 + 59)
+ let cse_var_64: int32 = (cse_var_110 + 58)
+ let cse_var_63: int32 = (cse_var_110 + 57)
+ let cse_var_62: int32 = (cse_var_110 + 56)
+ let cse_var_61: int32 = (cse_var_110 + 55)
+ let cse_var_60: int32 = (cse_var_110 + 54)
+ let cse_var_59: int32 = (cse_var_110 + 53)
+ let cse_var_58: int32 = (cse_var_110 + 52)
+ let cse_var_57: int32 = (cse_var_110 + 51)
+ let cse_var_56: int32 = (cse_var_110 + 50)
+ let cse_var_55: int32 = (cse_var_110 + 5)
+ let cse_var_54: int32 = (cse_var_110 + 49)
+ let cse_var_53: int32 = (cse_var_110 + 48)
+ let cse_var_52: int32 = (cse_var_110 + 47)
+ let cse_var_51: int32 = (cse_var_110 + 46)
+ let cse_var_50: int32 = (cse_var_110 + 45)
+ let cse_var_49: int32 = (cse_var_110 + 44)
+ let cse_var_48: int32 = (cse_var_110 + 43)
+ let cse_var_47: int32 = (cse_var_110 + 42)
+ let cse_var_46: int32 = (cse_var_110 + 41)
+ let cse_var_45: int32 = (cse_var_110 + 40)
+ let cse_var_44: int32 = (cse_var_110 + 4)
+ let cse_var_43: int32 = (cse_var_110 + 39)
+ let cse_var_42: int32 = (cse_var_110 + 38)
+ let cse_var_41: int32 = (cse_var_110 + 37)
+ let cse_var_40: int32 = (cse_var_110 + 36)
+ let cse_var_39: int32 = (cse_var_110 + 35)
+ let cse_var_38: int32 = (cse_var_110 + 34)
+ let cse_var_37: int32 = (cse_var_110 + 33)
+ let cse_var_36: int32 = (cse_var_110 + 32)
+ let cse_var_35: int32 = (cse_var_110 + 31)
+ let cse_var_34: int32 = (cse_var_110 + 30)
+ let cse_var_33: int32 = (cse_var_110 + 3)
+ let cse_var_32: int32 = (cse_var_110 + 29)
+ let cse_var_31: int32 = (cse_var_110 + 28)
+ let cse_var_30: int32 = (cse_var_110 + 27)
+ let cse_var_29: int32 = (cse_var_110 + 26)
+ let cse_var_28: int32 = (cse_var_110 + 25)
+ let cse_var_27: int32 = (cse_var_110 + 24)
+ let cse_var_26: int32 = (cse_var_110 + 23)
+ let cse_var_25: int32 = (cse_var_110 + 22)
+ let cse_var_24: int32 = (cse_var_110 + 21)
+ let cse_var_23: int32 = (cse_var_110 + 20)
+ let cse_var_22: int32 = (cse_var_110 + 2)
+ let cse_var_21: int32 = (cse_var_110 + 19)
+ let cse_var_20: int32 = (cse_var_110 + 18)
+ let cse_var_19: int32 = (cse_var_110 + 17)
+ let cse_var_18: int32 = (cse_var_110 + 16)
+ let cse_var_17: int32 = (cse_var_110 + 15)
+ let cse_var_16: int32 = (cse_var_110 + 14)
+ let cse_var_15: int32 = (cse_var_110 + 13)
+ let cse_var_14: int32 = (cse_var_110 + 12)
+ let cse_var_13: int32 = (cse_var_110 + 11)
+ let cse_var_12: int32 = (cse_var_110 + 107)
+ let cse_var_11: int32 = (cse_var_110 + 106)
+ let cse_var_10: int32 = (cse_var_110 + 105)
+ let cse_var_9: int32 = (cse_var_110 + 104)
+ let cse_var_8: int32 = (cse_var_110 + 103)
+ let cse_var_7: int32 = (cse_var_110 + 102)
+ let cse_var_6: int32 = (cse_var_110 + 101)
+ let cse_var_5: int32 = (cse_var_110 + 100)
+ let cse_var_4: int32 = (cse_var_110 + 10)
+ let cse_var_3: int32 = (cse_var_110 + 1)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
}
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner) + 392)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3136)] = max((conv2d_nchw_1[7] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3143)] = max((conv2d_nchw_1[8] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3150)] = max((conv2d_nchw_1[9] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3157)] = max((conv2d_nchw_1[10] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3164)] = max((conv2d_nchw_1[11] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3171)] = max((conv2d_nchw_1[12] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3178)] = max((conv2d_nchw_1[13] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
}
}
@@ -362,7 +1246,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.249 ms
+ Execution time of this operator: 0.300 ms
@@ -412,17 +1296,17 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_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_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
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_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
- conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_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=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=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=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)
@@ -433,12 +1317,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
- compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
+ 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=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
@@ -459,14 +1343,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=9)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -484,63 +1368,698 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[162];
- __shared__ float kernel_shared[288];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[9216];
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[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 9)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 9) + 1)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 2)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 3)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 5)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 4)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 4)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 5)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 3)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 6)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 2)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 7)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 8)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 10)];
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((3 <= ((((int)threadIdx.x) + 10) % 27)) && (((((int)threadIdx.x) + 10) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 24) {
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = ((((((int)threadIdx.x) < 21) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 1)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4608)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 4672)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4736)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4736) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4800)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4800) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4864)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4864) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4992)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5056)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5056) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5120)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5184)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 5248)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5312)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5312) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5376) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5440)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5440) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5504)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5568)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5632)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5696)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5760)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5824) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5888)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5888) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5952)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5952) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6016)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6016) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6080)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6144)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6208)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6336)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 6400)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6464)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6528)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6528) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6592)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6592) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6656)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6720) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6784)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6848)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6912)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 6976)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6976) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7040)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7040) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7104)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7104) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7232)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7296)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7360)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7424)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7488)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 7552)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7552) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7680)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7744)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7744) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7808)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7872)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7872) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7936)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8000)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 8128)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8192)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8256)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8320)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8384)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8448)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8576)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8576) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8640)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 8704)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8768)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8832)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8896)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 9024)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 9088)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9088) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 9152)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9152) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 144)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 147)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 150)]));
- }
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rc_outer_inner * 108)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rc_outer_inner * 108)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 54)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 54)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 78)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 78)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 81)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 81)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 105)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 105)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 55)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 55)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 79)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 79)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 82)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 82)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 106)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 106)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 56)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 56)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 80)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 80)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 83)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 83)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 107)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 107)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner) + 392)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3136)] = max((conv2d_nchw[7] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3143)] = max((conv2d_nchw[8] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3150)] = max((conv2d_nchw[9] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3157)] = max((conv2d_nchw[10] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3164)] = max((conv2d_nchw[11] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3171)] = max((conv2d_nchw[12] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3178)] = max((conv2d_nchw[13] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
}
@@ -601,7 +2120,7 @@ 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 14.918 seconds)
+ **Total running time of the script:** ( 3 minutes 26.775 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 2111e2339..7b5a1be6b 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)
- 10.1906 10.2254 10.2505 10.0959 0.0678
+ 9.8669 9.8798 9.8946 9.8263 0.0293
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 463ccdfe2..4c77c0b6e 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)
- 751.5250 751.2559 752.9956 750.3234 1.1074
+ 763.3407 762.9830 764.3289 762.7103 0.7075
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.922 seconds)
+ **Total running time of the script:** ( 1 minutes 22.267 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 4179e3403..5424a064f 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
@@ -397,29 +397,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (nb_j.inner: int32, 0, 2) {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
for (i.inner.init: int32, 0, 4) {
for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [128], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
for (i.inner: int32, 0, 4) {
for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 4) {
- let cse_var_4: int32 = (((i0.outer*2048) + (i0.inner*512)) + (i1.outer*32))
- compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -475,7 +476,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.235 ms
+ Execution time of this operator: 1.452 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 eaf0292f0..a50a6222f 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:46.359** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.017** 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``) | 00:46.324 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.981 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 6e7e763b1..88c5b4858 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: 188.85/188.85 result: MeasureResult(costs=(0.0012258750111111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0600717067718506, timestamp=1661223828.9150054) [('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: 0.00/188.85 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 80.73/80.73 result: MeasureResult(costs=(0.002867500257142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8834233283996582, timestamp=1661244463.0365772) [('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: 0.00/80.73 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: 260.69/260.69 result: MeasureResult(costs=(0.0008880194309392265,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.669468641281128, timestamp=1661223829.818118) [('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: 0.00/260.69 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 261.00/261.00 result: MeasureResult(costs=(0.0008869873701657459,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4214684963226318, timestamp=1661244463.8954568) [('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: 0.00/261.00 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: 0.00/260.69 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/261.00 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: 0.00/260.69 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/261.00 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: 5.26/260.69 result: MeasureResult(costs=(0.04400975375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8418543338775635, timestamp=1661223834.3559484) [('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: 3.35/260.69 result: MeasureResult(costs=(0.06910109149999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.501275300979614, timestamp=1661223835.5905685) [('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: 0.00/260.69 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.49/261.00 result: MeasureResult(costs=(0.04217780425,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8148174285888672, timestamp=1661244468.4581046) [('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: 3.34/261.00 result: MeasureResult(costs=(0.06938481925000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.559957504272461, timestamp=1661244469.704005) [('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: 0.00/261.00 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: 28.07/260.69 result: MeasureResult(costs=(0.008247764857142858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3089728355407715, timestamp=1661223846.6293054) [('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: 0.00/260.69 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 25.97/261.00 result: MeasureResult(costs=(0.008912912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1464619636535645, timestamp=1661244480.6022627) [('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: 0.00/261.00 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: 0.00/260.69 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/261.00 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: 0.001277
+ Time cost of this operator: 0.001254
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 d46e09b4a..c96b94f29 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 304.2 98.701 (1, 2, 10, 10, 3) 2 1 [304.2]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.053 0.99 (1, 6, 10, 10) 1 1 [3.053]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.309 (1, 1, 10, 10, 3) 1 1 [0.952]
- Total_time - 308.205 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.0 98.731 (1, 2, 10, 10, 3) 2 1 [311.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.03 0.962 (1, 6, 10, 10) 1 1 [3.03]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.307 (1, 1, 10, 10, 3) 1 1 [0.968]
+ Total_time - 314.998 - - - - -
@@ -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 195.8 98.676 (1, 6, 10, 10, 1) 2 1 [195.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.78 0.897 (1, 6, 10, 10) 1 1 [1.78]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.847 0.427 (1, 3, 10, 10, 1) 1 1 [0.847]
- Total_time - 198.427 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.375 96.71 (1, 6, 10, 10, 1) 2 1 [80.375]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.775 2.136 (1, 6, 10, 10) 1 1 [1.775]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.959 1.154 (1, 1, 10, 10, 3) 1 1 [0.959]
+ Total_time - 83.109 - - - - -
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 4981cd597..acee51d2c 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/tmp9gq1s984/images/random'
+ '/tmp/tmpanpuckf6/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp9gq1s984/images/target contains 8144 images
- /tmp/tmp9gq1s984/images/random contains 5000 images
+ /tmp/tmpanpuckf6/images/target contains 8144 images
+ /tmp/tmpanpuckf6/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 54s - loss: 0.2070 - accuracy: 0.9267 - val_loss: 0.1239 - val_accuracy: 0.9592
+ 328/328 - 55s - loss: 0.2198 - accuracy: 0.9231 - val_loss: 0.1355 - val_accuracy: 0.9607
Epoch 2/3
- 328/328 - 52s - loss: 0.0938 - accuracy: 0.9656 - val_loss: 0.1060 - val_accuracy: 0.9668
+ 328/328 - 52s - loss: 0.0979 - accuracy: 0.9637 - val_loss: 0.1210 - val_accuracy: 0.9645
Epoch 3/3
- 328/328 - 52s - loss: 0.0605 - accuracy: 0.9767 - val_loss: 0.1311 - val_accuracy: 0.9603
+ 328/328 - 52s - loss: 0.0685 - accuracy: 0.9743 - val_loss: 0.1145 - val_accuracy: 0.9649
- <keras.callbacks.History object at 0x7f3ca86d5110>
+ <keras.callbacks.History object at 0x7f6cad2dfb90>
@@ -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 6.391 seconds)
+ **Total running time of the script:** ( 4 minutes 55.340 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 de156d054..6254bfeff 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
=================
-**05:59.437** total execution time for **how_to_work_with_microtvm** files:
+**05:48.653** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:06.391 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:55.340 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.046 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.994 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.803 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.042 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.195 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.275 | 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 e5ecb7b84..981279038 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
=================
-**00:41.650** total execution time for **how_to_work_with_relay** files:
+**00:42.745** 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``) | 00:30.651 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.312 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.658 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.889 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.335 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.538 | 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 226c7daa4..4c43aa7c2 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 0x7f3c149bd170>
+ <function my_cuda_math_rule at 0x7f6c375d90e0>
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 81c124fa5..cbb7eb4be 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
@@ -5,18 +5,18 @@
Computation times
=================
-**00:03.886** total execution time for **how_to_work_with_schedules** files:
+**00:04.227** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.818 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.947 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.870 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.026 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.510 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.542 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.528 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.105 | 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 |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 b9d6fe1c0..cae37f6b6 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/tmp3_98ccsz/input0.cc'\nsource_filename = \"/tmp/tmp3_98ccsz/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/tmp_d_uffj2/input0.cc'\nsource_filename = \"/tmp/tmp_d_uffj2/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 6466cc56f..719ed4214 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
=================
-**00:21.406** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.053** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.399 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.046 | 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 d4a581e90..2cce9942d 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.88s!
+ resnet18_v1 inference graph built in 22.86s!
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 972080243..648977c6b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.87s!
+ yolov3-tiny inference graph built in 16.10s!
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 c47c0865d..7e270bbb0 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
=================
-**01:31.096** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.017** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.287 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.772 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.809 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.246 | 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 d595f274d..e7933b409 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
=================
-**00:03.201** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.385** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.813 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.971 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.388 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.414 | 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 7ff5f28fd..08675fe51 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
=================
-**00:00.696** total execution time for **topic_vta_tutorials** files:
+**00:00.771** 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``) | 00:00.402 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.321 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.369 | 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 e50f8cade..0f3e261f7 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: 92.551 ms
+ Execution time of this operator: 94.568 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index a2493921a..904ab13b4 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: 10.72/10.72 result: MeasureResult(costs=(0.0250505048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5350730419158936, timestamp=1661222640.539018) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.91/10.72 result: MeasureResult(costs=(0.0922622846,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6240155696868896, timestamp=1661222642.1854763) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.95/11.95 result: MeasureResult(costs=(0.022465997600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5506978034973145, timestamp=1661222643.2433298) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.78/11.95 result: MeasureResult(costs=(0.15057060100000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5330920219421387, timestamp=1661222646.346556) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.76/11.95 result: MeasureResult(costs=(0.07148399799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2783560752868652, timestamp=1661222647.755876) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.80/11.95 result: MeasureResult(costs=(0.1489843268,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.551570177078247, timestamp=1661222650.3522766) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.88/11.95 result: MeasureResult(costs=(0.305054975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.998769998550415, timestamp=1661222655.9184394) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.54/11.95 result: MeasureResult(costs=(0.025462705000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5463662147521973, timestamp=1661222656.4874182) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.75/11.95 result: MeasureResult(costs=(0.1531640826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.549555540084839, timestamp=1661222659.1571317) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.44/11.95 result: MeasureResult(costs=(0.10983492819999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.859569787979126, timestamp=1661222661.0761063) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.58/9.58 result: MeasureResult(costs=(0.028032059400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5825996398925781, timestamp=1661243257.8703933) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.72/9.58 result: MeasureResult(costs=(0.0986421146,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7145910263061523, timestamp=1661243259.6102347) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.022672648799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5500392913818359, timestamp=1661243260.6846845) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.57/11.84 result: MeasureResult(costs=(0.1708475746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.859412670135498, timestamp=1661243264.108421) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.70/11.84 result: MeasureResult(costs=(0.0724912362,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3039016723632812, timestamp=1661243265.537487) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.83/11.84 result: MeasureResult(costs=(0.1468703952,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5044596195220947, timestamp=1661243268.0899267) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.88/11.84 result: MeasureResult(costs=(0.3063590632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.021007537841797, timestamp=1661243273.690963) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.40/11.84 result: MeasureResult(costs=(0.0258117624,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5625371932983398, timestamp=1661243274.265915) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.58/11.84 result: MeasureResult(costs=(0.1703779124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8350937366485596, timestamp=1661243277.2198384) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.77/11.84 result: MeasureResult(costs=(0.0968355918,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6580238342285156, timestamp=1661243278.930646) [('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 b6c28f20c..022d58305 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': 492.48641366999436, 'median': 492.1965809500307, 'std': 0.8522537710826755}
+ {'mean': 491.82149348000166, 'median': 491.77043189997676, 'std': 1.0117483041688307}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: 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) | 6.27 s
[Task 1/25] Current/Best: 6.16/ 17.55 GFLOPS | Progress: (8/20) | 9.19 s
[Task 1/25] Current/Best: 11.55/ 22.71 GFLOPS | Progress: (12/20) | 11.62 s
[Task 1/25] Current/Best: 16.43/ 22.71 GFLOPS | Progress: (16/20) | 13.30 s
[Task 1/25] Current/Best: 11.63/ 23.81 GFLOPS | Progress: (20/20) | 15.05 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.10/ 12.95 GFLOPS | Progress: (4/20) | 3.65 s
[Task 2/25] Current/Best: 13.92/ 18.66 GFLOPS | Progress: (8/20) | 4.94 s
[Task 2/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (12/20) | 6.30 s
[Task 2/25] Current/Best: 12.55/ 21.10 GFLOPS | Progress: (16/20) | 7.57 s
[Task 2/25] Current/Best: 19.35/ 21.10 GFLOPS | Progress: (20/20) | 9.11 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.84 GFLOPS | Progress: (4/20) | 5.87 s
[Task 3/25] Current/Best: 15.55/ 16.80 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 15.24/ 16.80 GFLOPS | Progress: (12/20) | 9.50 s
[Task 3/25] Current/Best: 7.29/ 24.03 GFLOPS | Progress: (16/20) | 11.44 s
[Task 3/25] Current/Best: 12.28/ 24.03 GFLOPS | Progress: (20/20) | 15.98 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.66/ 20.64 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.84/ 20.64 GFLOPS | Progress: (8/20) | 6.70 s
[Task 4/25] Current/Best: 22.22/ 22.22 GFLOPS | Progress: (12/20) | 11.14 s
[Task 4/25] Current/Best: 17.29/ 22.22 GFLOPS | Progress: (16/20) | 13.39 s
[Task 4/25] Current/Best: 13.36/ 22.22 GFLOPS | Progress: (20/20) | 15.41 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.77/ 10.40 GFLOPS | Progress: (4/20) | 2.61 s
[Task 5/25] Current/Best: 11.72/ 12.76 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 11.28/ 18.03 GFLOPS | Progress: (12/20) | 7.64 s
[Task 5/25] Current/Best: 11.95/ 22.72 GFLOPS | Progress: (16/20) | 9.05 s
[Task 5/25] Current/Best: 11.92/ 22.72 GFLOPS | Progress: (20/20) | 10.91 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.28/ 20.64 GFLOPS | Progress: (4/20) | 3.97 s
[Task 6/25] Current/Best: 19.02/ 20.64 GFLOPS | Progress: (8/20) | 5.73 s
[Task 6/25] Current/Best: 13.29/ 20.64 GFLOPS | Progress: (12/20) | 7.65 s
[Task 6/25] Current/Best: 19.81/ 20.64 GFLOPS | Progress: (16/20) | 9.93 s
[Task 6/25] Current/Best: 3.76/ 20.64 GFLOPS | Progress: (20/20) | 12.47 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.07/ 12.86 GFLOPS | Progress: (4/20) | 3.68 s
[Task 7/25] Current/Best: 20.34/ 21.09 GFLOPS | Progress: (8/20) | 5.20 s
[Task 7/25] Current/Best: 15.91/ 21.09 GFLOPS | Progress: (12/20) | 7.11 s
[Task 7/25] Current/Best: 12.23/ 21.09 GFLOPS | Progress: (16/20) | 9.16 s
[Task 7/25] Current/Best: 6.30/ 21.75 GFLOPS | Progress: (20/20) | 11.62 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.91/ 14.06 GFLOPS | Progress: (4/20) | 2.95 s
[Task 8/25] Current/Best: 9.39/ 14.06 GFLOPS | Progress: (8/20) | 7.71 s
[Task 8/25] Current/Best: 12.46/ 14.06 GFLOPS | Progress: (12/20) | 13.82 s
[Task 8/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (16/20) | 15.91 s
[Task 8/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (20/20) | 22.36 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/ 15.89 GFLOPS | Progress: (4/20) | 11.98 s
[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.73 s
[Task 9/25] Current/Best: 8.26/ 23.47 GFLOPS | Progress: (12/20) | 16.07 s
[Task 9/25] Current/Best: 17.98/ 23.47 GFLOPS | Progress: (16/20) | 18.60 s
[Task 9/25] Current/Best: 9.19/ 23.47 GFLOPS | Progress: (20/20) | 26.08 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (4/20) | 2.59 s
[Task 10/25] Current/Best: 15.57/ 18.25 GFLOPS | Progress: (8/20) | 4.17 s
[Task 10/25] Current/Best: 12.25/ 18.96 GFLOPS | Progress: (12/20) | 5.69 s
[Task 10/25] Current/Best: 19.10/ 20.33 GFLOPS | Progress: (16/20) | 6.80 s
[Task 10/25] Current/Best: 8.95/ 20.33 GFLOPS | Progress: (20/20
) | 8.33 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.09/ 18.16 GFLOPS | Progress: (4/20) | 3.33 s
[Task 11/25] Current/Best: 15.03/ 18.16 GFLOPS | Progress: (8/20) | 6.06 s
[Task 11/25] Current/Best: 18.08/ 18.16 GFLOPS | Progress: (12/20) | 8.12 s
[Task 11/25] Current/Best: 13.47/ 20.89 GFLOPS | Progress: (16/20) | 10.89 s
[Task 11/25] Current/Best: 19.46/ 21.57 GFLOPS | Progress: (20/20) | 12.90 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 18.03 GFLOPS | Progress: (4/20) | 5.37 s
[Task 12/25] Current/Best: 5.30/ 18.03 GFLOPS | Progress: (8/20) | 9.05 s
[Task 12/25] Current/Best: 18.74/ 18.87 GFLOPS | Progress: (12/20) | 11.04 s
[Task 12/25] Current/Best: 15.52/ 18.87 GFLOPS | Progress: (16/20) | 13.77 s
[Task 12/25] Current/Best: 15.10/ 18.87 GFLOPS | Progress: (20/20) | 15.69 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.70/ 17.40 GFLOPS | Progress: (4/20) | 3.65 s
[Task 13/25] Current/Best: 15.94/ 20.97 GFLOPS | Progress: (8/20) | 6.08 s
[Task 13/25] Current/Best: 19.61/ 21.88 GFLOPS | Progress: (12/20) | 8.99 s
[Task 13/25] Current/Best: 12.28/ 21.88 GFLOPS | Progress: (16/20) | 12.36 s
[Task 13/25] Current/Best: 18.95/ 21.88 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: 13.69/ 13.69 GFLOPS | Progress: (4/20) | 3.33 s
[Task 14/25] Current/Best: 6.19/ 13.69 GFLOPS | Progress: (8/20) | 5.51 s
[Task 14/25] Current/Best: 20.24/ 20.24 GFLOPS | Progress: (12/20) | 8.05 s
[Task 14/25] Current/Best: 16.64/ 20.24 GFLOPS | Progress: (16/20) | 9.73 s Done.
-
[Task 14/25] Current/Best: 17.45/ 20.24 GFLOPS | Progress: (20/20) | 11.48 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.42/ 17.82 GFLOPS | Progress: (4/20) | 2.74 s
[Task 15/25] Current/Best: 14.59/ 18.26 GFLOPS | Progress: (8/20) | 4.07 s
[Task 15/25] Current/Best: 10.46/ 22.53 GFLOPS | Progress: (12/20) | 6.13 s
[Task 15/25] Current/Best: 20.70/ 22.53 GFLOPS | Progress: (16/20) | 9.13 s
[Task 15/25] Current/Best: 9.82/ 22.53 GFLOPS | Progress: (20/20) | 10.10 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (4/20) | 2.94 s
[Task 16/25] Current/Best: 3.07/ 20.74 GFLOPS | Progress: (8/20) | 4.54 s
[Task 16/25] Current/Best: 19.82/ 20.74 GFLOPS | Progress: (12/20) | 5.75 s
[Task 16/25] Current/Best: 17.76/ 20.74 GFLOPS | Progress: (16/20) |
7.10 s
[Task 16/25] Current/Best: 10.20/ 22.37 GFLOPS | Progress: (20/20) | 9.11 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.29/ 18.31 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 14.44/ 23.59 GFLOPS | Progress: (8/20) | 7.53 s
[Task 17/25] Current/Best: 18.76/ 23.59 GFLOPS | Progress: (12/20) | 9.59 s
[Task 17/25] Current/Best: 16.65/ 23.59 GFLOPS | Progress: (16/20) | 11.71 s
[Task 17/25] Current/Best: 10.15/ 23.59 GFLOPS | Progress: (20/20) | 13.81 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.48/ 17.46 GFLOPS | Progress: (4/20) | 3.72 s
[Task 18/25] Current/Best: 10.68/ 19.43 GFLOPS | Progress: (8/20) | 7.11 s
[Task 18/25] Current/Best: 19.56/ 19.56 GFLOPS | Progress: (12/20) | 9.04 s
[Task 18/25] Current/Best: 10.18/ 19.56 GFLOPS | Progress: (16/20) | 12.58 s
[Task 18/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (20/20) | 14.08 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.27/ 20.56 GFLOPS | Progress: (4/20) | 5.99 s
[Task 19/25] Current/Best: 2.72/ 20.56 GFLOPS | Progress: (8/20) | 9.20 s
[Task 19/25] Current/Best: 19.87/ 21.53 GFLOPS | Progress: (12/20) | 11.97 s
[Task 19/25] Current/Best: 15.23/ 22.21 GFLOPS | Progress: (16/20) | 14.80 s
[Task 19/25] Current/Best: 2.73/ 23.24 GFLOPS | Progress: (20/20) | 17.60 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.66/ 15.60 GFLOPS | Progress: (4/20) | 3.34 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (4/20) | 6.35 s
[Task 1/25] Current/Best: 6.15/ 17.51 GFLOPS | Progress: (8/20) | 9.32 s
[Task 1/25] Current/Best: 11.52/ 22.77 GFLOPS | Progress: (12/20) | 11.74 s
[Task 1/25] Current/Best: 16.55/ 22.77 GFLOPS | Progress: (16/20) | 13.43 s
[Task 1/25] Current/Best: 11.62/ 23.82 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: 12.34/ 13.08 GFLOPS | Progress: (4/20) | 3.81 s
[Task 2/25] Current/Best: 14.15/ 18.66 GFLOPS | Progress: (8/20) | 5.12 s
[Task 2/25] Current/Best: 21.05/ 21.05 GFLOPS | Progress: (12/20) | 6.44 s
[Task 2/25] Current/Best: 12.19/ 21.05 GFLOPS | Progress: (16/20) | 7.68 s
[Task 2/25] Current/Best: 19.48/ 21.05 GFLOPS | Progress: (20/20) | 9.29 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/ 10.82 GFLOPS | Progress: (4/20) | 5.86 s
[Task 3/25] Current/Best: 15.28/ 16.78 GFLOPS | Progress: (8/20) | 7.79 s
[Task 3/25] Current/Best: 14.99/ 16.78 GFLOPS | Progress: (12/20) | 9.49 s
[Task 3/25] Current/Best: 7.22/ 23.63 GFLOPS | Progress: (16/20) | 11.44 s
[Task 3/25] Current/Best: 12.59/ 23.63 GFLOPS | Progress: (20/20) | 15.93 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.57/ 20.53 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.86/ 20.53 GFLOPS | Progress: (8/20) | 6.70 s
[Task 4/25] Current/Best: 22.47/ 22.47 GFLOPS | Progress: (12/20) | 11.23 s
[Task 4/25] Current/Best: 17.41/ 22.47 GFLOPS | Progress: (16/20) | 13.43 s
[Task 4/25] Current/Best: 13.48/ 22.47 GFLOPS | Progress: (20/20) | 15.41 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.73/ 10.45 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.75/ 12.87 GFLOPS | Progress: (8/20) | 4.70 s
[Task 5/25] Current/Best: 11.54/ 18.03 GFLOPS | Progress: (12/20) | 7.78 s
[Task 5/25] Current/Best: 11.80/ 22.46 GFLOPS | Progress: (16/20) | 9.19 s
[Task 5/25] Current/Best: 12.07/ 22.46 GFLOPS | Progress: (20/20) | 11.02 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.18/ 20.70 GFLOPS | Progress: (4/20) | 3.98 s
[Task 6/25] Current/Best: 18.98/ 20.70 GFLOPS | Progress: (8/20) | 5.75 s
[Task 6/25] Current/Best: 13.27/ 20.70 GFLOPS | Progress: (12/20) | 7.67 s
[Task 6/25] Current/Best: 19.91/ 20.70 GFLOPS | Progress: (16/20) | 9.92 s
[Task 6/25] Current/Best: 3.73/ 20.70 GFLOPS | Progress: (20/20) | 12.44 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.17/ 12.96 GFLOPS | Progress: (4/20) | 3.63 s
[Task 7/25] Current/Best: 20.36/ 21.08 GFLOPS | Progress: (8/20) | 5.14 s
[Task 7/25] Current/Best: 15.90/ 21.08 GFLOPS | Progress: (12/20) | 7.04 s
[Task 7/25] Current/Best: 12.26/ 21.08 GFLOPS | Progress: (16/20) | 9.07 s
[Task 7/25] Current/Best: 6.36/ 21.82 GFLOPS | Progress: (20/20) | 11.52 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.90/ 14.20 GFLOPS | Progress: (4/20) | 2.90 s
[Task 8/25] Current/Best: 9.44/ 14.20 GFLOPS | Progress: (8/20) | 7.63 s
[Task 8/25] Current/Best: 12.36/ 14.20 GFLOPS | Progress: (12/20) | 13.75 s
[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (16/20) | 15.87 s
[Task 8/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (20/20) | 22.31 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.31/ 15.72 GFLOPS | Progress: (4/20) | 12.00 s
[Task 9/25] Current/Best: 23.59/ 23.59 GFLOPS | Progress: (8/20) | 13.80 s
[Task 9/25] Current/Best: 8.24/ 23.59 GFLOPS | Progress: (12/20) | 16.17 s
[Task 9/25] Current/Best: 18.04/ 23.59 GFLOPS | Progress: (16/20) | 18.81 s
[Task 9/25] Current/Best: 9.20/ 23.59 GFLOPS | Progress: (20/20) | 26.48 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.29/ 18.29 GFLOPS | Progress: (4/20) | 2.58 s
[Task 10/25] Current/Best: 15.40/ 18.29 GFLOPS | Progress: (8/20) | 4.18 s
[Task 10/25] Current/Best: 12.63/ 18.95 GFLOPS | Progress: (12/20) | 5.71 s
[Task 10/25] Current/Best: 19.12/ 20.37 GFLOPS | Progress: (16/20) | 6.82 s
[Task 10/25] Current/Best: 8.87/ 20.37 GFLOPS | Progress: (20/20
) | 8.35 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.30/ 18.09 GFLOPS | Progress: (4/20) | 3.30 s
[Task 11/25] Current/Best: 16.84/ 18.09 GFLOPS | Progress: (8/20) | 6.01 s
[Task 11/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (12/20) | 8.07 s
[Task 11/25] Current/Best: 13.44/ 21.02 GFLOPS | Progress: (16/20) | 10.83 s
[Task 11/25] Current/Best: 19.50/ 21.64 GFLOPS | Progress: (20/20) | 12.85 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 18.07 GFLOPS | Progress: (4/20) | 5.38 s
[Task 12/25] Current/Best: 5.26/ 18.07 GFLOPS | Progress: (8/20) | 9.09 s
[Task 12/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (12/20) | 11.08 s
[Task 12/25] Current/Best: 15.48/ 18.99 GFLOPS | Progress: (16/20) | 13.87 s
[Task 12/25] Current/Best: 15.18/ 18.99 GFLOPS | Progress: (20/20) | 15.82 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.47/ 17.29 GFLOPS | Progress: (4/20) | 3.73 s
[Task 13/25] Current/Best: 15.66/ 20.92 GFLOPS | Progress: (8/20) | 6.15 s
[Task 13/25] Current/Best: 19.51/ 21.56 GFLOPS | Progress: (12/20) | 9.01 s
[Task 13/25] Current/Best: 12.30/ 21.56 GFLOPS | Progress: (16/20) | 12.42 s
[Task 13/25] Current/Best: 18.60/ 21.56 GFLOPS | Progress: (20/20) | 14.72 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.66/ 13.66 GFLOPS | Progress: (4/20) | 3.34 s
[Task 14/25] Current/Best: 6.10/ 13.66 GFLOPS | Progress: (8/20) | 5.54 s
[Task 14/25] Current/Best: 20.27/ 20.27 GFLOPS | Progress: (12/20) | 8.06 s
[Task 14/25] Current/Best: 16.87/ 20.27 GFLOPS | Progress: (16/20) | 9.70 s Done.
+
[Task 14/25] Current/Best: 17.00/ 20.27 GFLOPS | Progress: (20/20) | 11.53 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.16/ 17.59 GFLOPS | Progress: (4/20) | 2.76 s
[Task 15/25] Current/Best: 14.26/ 17.97 GFLOPS | Progress: (8/20) | 4.06 s
[Task 15/25] Current/Best: 10.39/ 22.26 GFLOPS | Progress: (12/20) | 6.17 s
[Task 15/25] Current/Best: 20.39/ 22.26 GFLOPS | Progress: (16/20) | 9.01 s
[Task 15/25] Current/Best: 9.71/ 22.26 GFLOPS | Progress: (20/20) | 9.99 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.73/ 19.73 GFLOPS | Progress: (4/20) | 3.05 s
[Task 16/25] Current/Best: 3.00/ 19.73 GFLOPS | Progress: (8/20) | 4.67 s
[Task 16/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (12/20) | 5.91 s
[Task 16/25] Current/Best: 17.87/ 19.77 GFLOPS | Progress: (16/20) |
7.26 s
[Task 16/25] Current/Best: 10.02/ 22.13 GFLOPS | Progress: (20/20) | 9.29 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.43/ 18.28 GFLOPS | Progress: (4/20) | 4.71 s
[Task 17/25] Current/Best: 14.41/ 23.26 GFLOPS | Progress: (8/20) | 7.48 s
[Task 17/25] Current/Best: 17.05/ 23.26 GFLOPS | Progress: (12/20) | 9.54 s
[Task 17/25] Current/Best: 16.48/ 23.26 GFLOPS | Progress: (16/20) | 11.65 s
[Task 17/25] Current/Best: 10.06/ 23.26 GFLOPS | Progress: (20/20) | 13.77 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.20/ 17.70 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 10.54/ 19.93 GFLOPS | Progress: (8/20) | 7.10 s
[Task 18/25] Current/Best: 19.26/ 19.93 GFLOPS | Progress: (12/20) | 9.03 s
[Task 18/25] Current/Best: 10.11/ 19.93 GFLOPS | Progress: (16/20) | 12.62 s
[Task 18/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (20/20) | 14.13 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.20/ 20.30 GFLOPS | Progress: (4/20) | 5.97 s
[Task 19/25] Current/Best: 2.69/ 20.30 GFLOPS | Progress: (8/20) | 9.21 s
[Task 19/25] Current/Best: 19.75/ 21.68 GFLOPS | Progress: (12/20) | 12.02 s
[Task 19/25] Current/Best: 15.35/ 22.05 GFLOPS | Progress: (16/20) | 14.90 s
[Task 19/25] Current/Best: 2.70/ 23.25 GFLOPS | Progress: (20/20) | 17.75 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.40/ 15.30 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-
[Task 20/25] Current/Best: 9.76/ 15.60 GFLOPS | Progress: (8/20) | 6.60 s
[Task 20/25] Current/Best: 2.35/ 16.95 GFLOPS | Progress: (12/20) | 10.48 s
[Task 20/25] Current/Best: 11.82/ 16.95 GFLOPS | Progress: (16/20) | 14.15 s
[Task 20/25] Current/Best: 12.29/ 22.21 GFLOPS | Progress: (20/20) | 16.23 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.46/ 17.97 GFLOPS | Progress: (4/20) | 3.22 s
[Task 21/25] Current/Best: 14.72/ 17.97 GFLOPS | Progress: (8/20) | 4.80 s
[Task 21/25] Current/Best: 1.63/ 17.97 GFLOPS | Progress: (12/20) | 6.92 s
[Task 21/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (16/20) | 10.34 s
[Task 21/25] Current/Best: 4.47/ 18.09 GFLOPS | Progress: (20/20) | 17.40 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: 9.20/ 21.83 GFLOPS | Progress: (8/20) | 4.68 s
[Task 22/25] Current/Best: 19.94/ 21.83 GFLOPS | Progress: (12/20) | 7.00 s
[Task 22/25] Current/Best: 15.45/ 21.83 GFLOPS | Progress: (16/20) | 9.06 s
[Task 22/25] Current/Best: 14.30/ 21.83 GFLOPS | Progress: (20/20) | 10.71 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.76/ 21.06 GFLOPS | Progress: (4/20) | 3.22 s
[Task 23/25] Current/Best: 14.75/ 21.06 GFLOPS | Progress: (8/20) | 6.57 s
[Task 23/25] Current/Best: 21.01/ 21.60 GFLOPS | Progress: (12/20) | 8.36 s
[Task 23/25] Current/Best: 6.40/ 21.60 GFLOPS | Progress: (16/20) | 15.24 s
[Task 23/25] Current/Best: 7.87/ 21.60 GFLOPS | Progress: (20/20) | 19.42 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.62/ 8.62 GFLOPS | Progress: (4/20) | 11.81 s
[Task 24/25] Current/Best: 2.11/ 8.62 GFLOPS | Progress: (8/20) | 22.83 s
[Task 24/25] Current/Best: 4.42/ 8.62 GFLOPS | Progress: (12/20) | 34.37 s Done.
-
[Task 24/25] Current/Best: 6.34/ 8.67 GFLOPS | Progress: (16/20) | 39.75 s
[Task 24/25] Current/Best: 3.29/ 8.67 GFLOPS | Progress: (20/20) | 45.56 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/ 2.94 GFLOPS | Progress: (4/20) | 11.64 s
[Task 25/25] Current/Best: 5.58/ 7.91 GFLOPS | Progress: (8/20) | 22.93 s
[Task 25/25] Current/Best: 5.85/ 7.91 GFLOPS | Progress: (12/20) | 34.45 s
[Task 25/25] Current/Best: 5.74/ 9.35 GFLOPS | Progress: (16/20) | 36.34 s
[Task 25/25] Current/Best: 2.91/ 9.35 GFLOPS | Progress: (20/20) | 47.04 s
+
[Task 20/25] Current/Best: 9.63/ 15.30 GFLOPS | Progress: (8/20) | 6.76 s
[Task 20/25] Current/Best: 2.32/ 16.50 GFLOPS | Progress: (12/20) | 10.68 s
[Task 20/25] Current/Best: 12.38/ 16.50 GFLOPS | Progress: (16/20) | 14.37 s
[Task 20/25] Current/Best: 12.44/ 22.13 GFLOPS | Progress: (20/20) | 16.45 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.68 GFLOPS | Progress: (4/20) | 3.23 s
[Task 21/25] Current/Best: 14.65/ 17.68 GFLOPS | Progress: (8/20) | 4.79 s
[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 6.94 s
[Task 21/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (16/20) | 10.38 s
[Task 21/25] Current/Best: 4.45/ 18.14 GFLOPS | Progress: (20/20) | 17.35 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.97 GFLOPS | Progress: (4/20
) | 2.71 s
[Task 22/25] Current/Best: 8.71/ 21.83 GFLOPS | Progress: (8/20) | 4.69 s
[Task 22/25] Current/Best: 20.08/ 21.83 GFLOPS | Progress: (12/20) | 7.01 s
[Task 22/25] Current/Best: 15.28/ 21.83 GFLOPS | Progress: (16/20) | 9.08 s
[Task 22/25] Current/Best: 14.45/ 21.83 GFLOPS | Progress: (20/20) | 10.80 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.63/ 20.60 GFLOPS | Progress: (4/20) | 3.27 s
[Task 23/25] Current/Best: 13.73/ 20.60 GFLOPS | Progress: (8/20) | 6.65 s
[Task 23/25] Current/Best: 20.80/ 21.58 GFLOPS | Progress: (12/20) | 8.45 s
[Task 23/25] Current/Best: 6.24/ 21.58 GFLOPS | Progress: (16/20) | 15.34 s
[Task 23/25] Current/Best: 7.98/ 21.58 GFLOPS | Progress: (20/20) | 19.51 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.54/ 8.54 GFLOPS | Progress: (4/20) | 11.80 s
[Task 24/25] Current/Best: 2.14/ 8.54 GFLOPS | Progress: (8/20) | 22.81 s
[Task 24/25] Current/Best: 4.29/ 8.54 GFLOPS | Progress: (12/20) | 34.35 s Done.
+
[Task 24/25] Current/Best: 5.78/ 8.85 GFLOPS | Progress: (16/20) | 39.64 s
[Task 24/25] Current/Best: 2.97/ 8.85 GFLOPS | Progress: (20/20) | 45.48 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.78 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 5.87/ 7.94 GFLOPS | Progress: (8/20) | 22.88 s
[Task 25/25] Current/Best: 5.95/ 7.94 GFLOPS | Progress: (12/20) | 34.35 s
[Task 25/25] Current/Best: 5.85/ 9.00 GFLOPS | Progress: (16/20) | 36.09 s
[Task 25/25] Current/Best: 2.86/ 9.04 GFLOPS | Progress: (20/20) | 46.77 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 405.6382329199914, 'median': 405.48388540000815, 'std': 0.933472245333622}
- unoptimized: {'mean': 492.48641366999436, 'median': 492.1965809500307, 'std': 0.8522537710826755}
+ optimized: {'mean': 410.1723779999793, 'median': 410.00709689997166, 'std': 0.6558500357178145}
+ unoptimized: {'mean': 491.82149348000166, 'median': 491.77043189997676, 'std': 1.0117483041688307}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 13.849 seconds)
+ **Total running time of the script:** ( 10 minutes 15.354 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 bd21b989e..0955c405d 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
- 1.255e-07 secs/op
+ 1.305e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 8e026779a..ba19755f6 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, 0xdc06900)), stage(b, placeholder(b, 0x23622a20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x222d8bc0)), stage(b, placeholder(b, 0x20ffb4b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 73eb6a2a0..f45268260 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**13:01.733** total execution time for **tutorial** files:
+**13:09.642** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:13.849 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:15.354 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.483 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:59.913 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:53.391 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:57.582 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.654 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.581 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.999 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.557 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.700 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.793 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.503 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.703 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.148 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.152 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.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 |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :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 |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.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 2162d63a9..8f3580eb4 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000006
+ parallel: 0.000007
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.460670005661087e-06 1.0
- naive 5.831999999999999e-06 0.6893071111505084
- parallel 5.8522e-06 0.691694628922326
- vector 2.5397399999999995e-05 3.001819002869328
+ numpy 7.78373000684951e-06 1.0
+ naive 5.8138e-06 0.746916965887047
+ parallel 6.950399999999999e-06 0.8929395025114952
+ vector 2.4538099999999998e-05 3.1524860161396933
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017634
+ Numpy running time: 0.017927
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: 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: 3.252105
+ none: 3.154756
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.295339
+ blocking: 0.290210
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.332997
+ vectorization: 0.325854
@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:267: 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: 0.113340
+ loop permutation: 0.117447
@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:267: 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: 0.106468
+ array packing: 0.109963
@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:267: 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: 0.108536
+ block caching: 0.111333
@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:267: 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: 0.144063
+ parallelization: 0.144473
@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 3.2521051694 1.0
- blocking 0.2953391412 0.0908147571545138
- vectorization 0.33299698469999994 0.10239428534884575
- loop permutation 0.113339674 0.03485117119410708
- array packing 0.1064680815 0.032738203703185566
- block caching 0.10853594479999999 0.033374057463222945
- parallelization 0.144062898 0.04429835152796704
+ none 3.1547563393 1.0
+ blocking 0.29021008769999995 0.09199128442496254
+ vectorization 0.3258543642 0.10328986747429848
+ loop permutation 0.11744688699999999 0.03722851287654753
+ array packing 0.10996334910000001 0.03485636837626562
+ block caching 0.11133254470000001 0.03529037831324345
+ parallelization 0.1444727579 0.04579521914267923
diff --git a/docs/commit_hash b/docs/commit_hash
index bb9126ba9..f5fb9be0c 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-58f2139ffdd39de61fcea3b090dcfa5f7d0db4be
+383bd419310fac4d9d78e0c59760cbef3efa5555
diff --git a/docs/contribute/ci.html b/docs/contribute/ci.html
index 79279bbab..b8522fa97 100644
--- a/docs/contribute/ci.html
+++ b/docs/contribute/ci.html
@@ -381,9 +381,13 @@
</li>
<li><p><a class="reference internal" href="#dealing-with-flakiness" id="id11">Dealing with Flakiness</a></p></li>
<li><p><a class="reference internal" href="#skipping-ci" id="id12">Skipping CI</a></p></li>
-<li><p><a class="reference internal" href="#docker-images" id="id13">Docker Images</a></p></li>
-<li><p><a class="reference internal" href="#ci-docker-staging" id="id14"><code class="docutils literal notranslate"><span class="pre">ci-docker-staging</span></code></a></p></li>
-<li><p><a class="reference internal" href="#ci-monitoring-rotation" id="id15">CI Monitoring Rotation</a></p></li>
+<li><p><a class="reference internal" href="#docker-images" id="id13">Docker Images</a></p>
+<ul>
+<li><p><a class="reference internal" href="#adding-a-new-docker-image" id="id14">Adding a new Docker image</a></p></li>
+</ul>
+</li>
+<li><p><a class="reference internal" href="#ci-docker-staging" id="id15"><code class="docutils literal notranslate"><span class="pre">ci-docker-staging</span></code></a></p></li>
+<li><p><a class="reference internal" href="#ci-monitoring-rotation" id="id16">CI Monitoring Rotation</a></p></li>
</ul>
</li>
</ul>
@@ -505,9 +509,33 @@ files are built nightly in Jenkins via the <a class="reference external" href="h
The images for these containers are hosted in the <a class="reference external" href="https://hub.docker.com/u/tlcpack">tlcpack Docker Hub</a>
and referenced in the <a class="reference external" href="https://github.com/apache/tvm/tree/main/Jenkinsfile.j2">Jenkinsfile.j2</a>. These can be inspected and run
locally via standard Docker commands.</p>
+<div class="section" id="adding-a-new-docker-image">
+<h4><a class="toc-backref" href="#id14">Adding a new Docker image</a><a class="headerlink" href="#adding-a-new-docker-image" title="Permalink to this headline">¶</a></h4>
+<p>New docker images can be added to test TVM on a variety of platforms. Here are the steps for adding
+a new CI image:</p>
+<ol class="arabic">
+<li><p>Define the <code class="docutils literal notranslate"><span class="pre">docker/Dockerfile.ci_foo</span></code> and associated scripts in <code class="docutils literal notranslate"><span class="pre">docker/install</span></code>. Create a PR containing only these changes (no <code class="docutils literal notranslate"><span class="pre">Jenkinsfile</span></code> changes).</p>
+<p>Example: <a class="reference external" href="https://github.com/apache/tvm/pull/12230/files">https://github.com/apache/tvm/pull/12230/files</a></p>
+</li>
+<li><p>A committer verifies the image builds locally and then reviews/approves this PR.</p></li>
+<li><p>A committer creates the ci-foo repos in <a class="reference external" href="https://hub.docker.com/u/tlcpack">https://hub.docker.com/u/tlcpack</a> and <a class="reference external" href="https://hub.docker.com/u/tlcpackstaging">https://hub.docker.com/u/tlcpackstaging</a>.</p></li>
+<li><p>Create a PR to create an ECR repo for the image in tlcpack/ci: <a class="reference external" href="https://github.com/tlc-pack/ci/pull/46/files">https://github.com/tlc-pack/ci/pull/46/files</a></p></li>
+<li><p>A committer creates and gets merged a PR to add the image to the <code class="docutils literal notranslate"><span class="pre">Jenkinsfile</span></code></p>
+<blockquote>
+<div><p>Example: <a class="reference external" href="https://github.com/apache/tvm/pull/12369/files">https://github.com/apache/tvm/pull/12369/files</a>.</p>
+<p><strong>NOTE</strong>: The PR must be opened from a branch in apache/tvm, not from a branch in a forked repo.</p>
+</div></blockquote>
+</li>
+<li><p>A committer adds this image to the daily docker rebuild/validation run in tlcpack.</p>
+<blockquote>
+<div><p>Example: <a class="reference external" href="https://github.com/tlc-pack/tlcpack/pull/131">https://github.com/tlc-pack/tlcpack/pull/131</a></p>
+</div></blockquote>
+</li>
+</ol>
+</div>
</div>
<div class="section" id="ci-docker-staging">
-<h3><a class="toc-backref" href="#id14"><code class="docutils literal notranslate"><span class="pre">ci-docker-staging</span></code></a><a class="headerlink" href="#ci-docker-staging" title="Permalink to this headline">¶</a></h3>
+<h3><a class="toc-backref" href="#id15"><code class="docutils literal notranslate"><span class="pre">ci-docker-staging</span></code></a><a class="headerlink" href="#ci-docker-staging" title="Permalink to this headline">¶</a></h3>
<p>The <a class="reference external" href="https://github.com/apache/tvm/tree/ci-docker-staging">ci-docker-staging</a>
branch is typically used to test updates to Docker images and <code class="docutils literal notranslate"><span class="pre">Jenkinsfile</span></code> changes. When
running a build for a normal PR from a forked repository, Jenkins uses the code
@@ -519,7 +547,7 @@ to @ a <a class="reference external" href="https://github.com/apache/tvm/tre
and ask them to push your PR as a branch to test the changes.</p>
</div>
<div class="section" id="ci-monitoring-rotation">
-<h3><a class="toc-backref" href="#id15">CI Monitoring Rotation</a><a class="headerlink" href="#ci-monitoring-rotation" title="Permalink to this headline">¶</a></h3>
+<h3><a class="toc-backref" href="#id16">CI Monitoring Rotation</a><a class="headerlink" href="#ci-monitoring-rotation" title="Permalink to this headline">¶</a></h3>
<p>Some tests are also flaky and occasionally fail for reasons unrelated to the PR. The
<a class="reference external" href="https://github.com/apache/tvm/wiki/CI-Monitoring-Runbook">CI monitoring rotation</a> watches for these failures and
disables tests as necessary. It is the responsibility of those who wrote the test to ultimately fix
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 47ac9ebdb..531bdbf9c 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 2.307 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.543 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 bba15ffaa..eeebbda74 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.zip3b333d2c-aed8-4b57-b607-d42b4e5c6f12 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.zip16c13765-9594-44c2-b482-af293cb91e96 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 3d606aa88..8e9879cfb 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,12 +432,12 @@ 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]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 56.0MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 54.5MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 53.9MB/s]
- 66%|######6 | 27.5M/41.5M [00:00<00:00, 48.3MB/s]
- 82%|########2 | 34.1M/41.5M [00:00<00:00, 51.1MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 56.8MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 55.3MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 62.1MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 53.3MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 59.7MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 48.7MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 53.3MB/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 c40514ff3..f4c035beb 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +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]
- 37%|###6 | 16.3M/44.7M [00:00<00:00, 171MB/s]
- 78%|#######8 | 34.9M/44.7M [00:00<00:00, 185MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 153MB/s]
+ 39%|###9 | 17.5M/44.7M [00:00<00:00, 184MB/s]
+ 92%|#########1| 40.9M/44.7M [00:00<00:00, 220MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 218MB/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 077a579e3..32a67f2f0 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 1.691 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.987 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 1cf495a7b..22e808832 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>04:57.387</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:05.836</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_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>01:02.307</p></td>
+<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>01:04.987</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:01.691</p></td>
+<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>01:02.543</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>00:38.511</p></td>
+<td><p>00:39.248</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>00:27.517</p></td>
+<td><p>00:28.668</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>00:25.018</p></td>
+<td><p>00:26.182</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.011</p></td>
+<td><p>00:25.242</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>00:22.694</p></td>
+<td><p>00:22.168</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>00:19.039</p></td>
+<td><p>00:19.470</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>00:13.664</p></td>
+<td><p>00:14.845</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>00:02.936</p></td>
+<td><p>00:02.481</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 ece0da341..bcdc17866 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)
- 15.4482 15.4740 15.6752 15.2577 0.1224
+ 15.8027 15.8138 16.0244 15.6502 0.1103
</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 c4cc482bc..53e0d395e 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,19 +436,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/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]
- 5%|5 | 8.73M/170M [00:00<00:01, 91.5MB/s]
- 10%|# | 17.5M/170M [00:00<00:01, 89.6MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:01, 118MB/s]
- 27%|##6 | 45.2M/170M [00:00<00:01, 126MB/s]
- 34%|###3 | 57.2M/170M [00:00<00:01, 114MB/s]
- 40%|#### | 68.3M/170M [00:00<00:00, 111MB/s]
- 47%|####6 | 79.0M/170M [00:00<00:00, 104MB/s]
- 59%|#####8 | 99.5M/170M [00:00<00:00, 136MB/s]
- 70%|######9 | 118M/170M [00:00<00:00, 154MB/s]
- 79%|#######8 | 133M/170M [00:01<00:00, 149MB/s]
- 87%|########7 | 148M/170M [00:01<00:00, 118MB/s]
- 94%|#########4| 160M/170M [00:01<00:00, 109MB/s]
-100%|##########| 170M/170M [00:01<00:00, 118MB/s]
+ 9%|9 | 15.9M/170M [00:00<00:00, 167MB/s]
+ 22%|##2 | 38.2M/170M [00:00<00:00, 206MB/s]
+ 36%|###5 | 60.8M/170M [00:00<00:00, 220MB/s]
+ 50%|####9 | 84.4M/170M [00:00<00:00, 231MB/s]
+ 65%|######5 | 111M/170M [00:00<00:00, 248MB/s]
+ 81%|########1 | 138M/170M [00:00<00:00, 259MB/s]
+ 97%|#########6| 164M/170M [00:00<00:00, 265MB/s]
+100%|##########| 170M/170M [00:00<00:00, 245MB/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').
@@ -543,7 +538,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 53.986 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 54.528 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 e1cabc6af..129694783 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,9 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 144MB/s]
+ 28%|##8 | 3.80M/13.6M [00:00<00:00, 39.0MB/s]
+ 65%|######4 | 8.78M/13.6M [00:00<00:00, 46.7MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 61.2MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +571,7 @@ 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)
- 89.2087 89.1286 92.8700 88.8271 0.4262
+ 90.4212 90.0720 104.3539 89.9028 1.7381
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +610,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.614 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.468 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 56e02b31d..514e34cf0 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)
- 122.8810 122.6769 131.6116 121.7623 1.1060
+ 120.7667 120.7356 123.0604 119.2780 0.5273
</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 55.424 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.307 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 ce8110d63..0fc730437 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 24.443 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.303 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 0acb1946e..89918b330 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +441,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|2 | 3597/132723 [00:00<00:03, 35967.46KB/s]
- 9%|8 | 11362/132723 [00:00<00:02, 60483.72KB/s]
- 14%|#4 | 18992/132723 [00:00<00:01, 67703.25KB/s]
- 21%|## | 27267/132723 [00:00<00:01, 73640.06KB/s]
- 26%|##6 | 34631/132723 [00:00<00:01, 71254.73KB/s]
- 32%|###2 | 42807/132723 [00:00<00:01, 74746.31KB/s]
- 38%|###8 | 51054/132723 [00:00<00:01, 77232.90KB/s]
- 45%|####4 | 59350/132723 [00:00<00:00, 79035.05KB/s]
- 51%|##### | 67591/132723 [00:00<00:00, 80080.94KB/s]
- 57%|#####7 | 75979/132723 [00:01<00:00, 81241.04KB/s]
- 64%|######3 | 84321/132723 [00:01<00:00, 81903.69KB/s]
- 70%|######9 | 92658/132723 [00:01<00:00, 82346.32KB/s]
- 76%|#######6 | 101032/132723 [00:01<00:00, 82764.66KB/s]
- 82%|########2 | 109485/132723 [00:01<00:00, 83294.44KB/s]
- 89%|########8 | 117817/132723 [00:01<00:00, 83065.73KB/s]
- 95%|#########5| 126131/132723 [00:01<00:00, 83085.26KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 78455.00KB/s]
+ 5%|4 | 6230/132723 [00:00<00:02, 62292.49KB/s]
+ 11%|# | 14541/132723 [00:00<00:01, 74529.57KB/s]
+ 17%|#7 | 23041/132723 [00:00<00:01, 79305.13KB/s]
+ 24%|##3 | 31492/132723 [00:00<00:01, 81357.42KB/s]
+ 30%|### | 39913/132723 [00:00<00:01, 82382.49KB/s]
+ 36%|###6 | 48346/132723 [00:00<00:01, 83038.50KB/s]
+ 43%|####2 | 56834/132723 [00:00<00:00, 83637.30KB/s]
+ 49%|####9 | 65295/132723 [00:00<00:00, 83945.36KB/s]
+ 56%|#####5 | 73849/132723 [00:00<00:00, 84440.14KB/s]
+ 62%|######2 | 82294/132723 [00:01<00:00, 84380.18KB/s]
+ 68%|######8 | 90733/132723 [00:01<00:00, 84267.86KB/s]
+ 75%|#######4 | 99160/132723 [00:01<00:00, 84190.42KB/s]
+ 81%|########1 | 107648/132723 [00:01<00:00, 84395.78KB/s]
+ 87%|########7 | 116100/132723 [00:01<00:00, 84431.22KB/s]
+ 94%|#########3| 124583/132723 [00:01<00:00, 84549.77KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83036.94KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -500,7 +499,7 @@ 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 33.210 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 34.620 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 838f3ee44..362ab3abe 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>11:08.572</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:08.593</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>02:53.986</p></td>
+<td><p>02:54.528</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>02:33.210</p></td>
+<td><p>02:34.620</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>01:55.424</p></td>
+<td><p>01:53.307</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>01:24.443</p></td>
+<td><p>01:24.303</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:08.614</p></td>
+<td><p>01:08.468</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.460</p></td>
+<td><p>00:29.632</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>00:21.765</p></td>
+<td><p>00:22.041</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>00:21.663</p></td>
+<td><p>00:21.688</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 4c89807e0..485f30a21 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.zip05ec726a-902c-4f2c-9818-ad5306d36f25 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.zip24645e29-09bb-418b-ac1e-a62aa744bfea 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 dcdb5f31a..7847a8d2d 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>00:41.134</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:41.330</strong> total execution time for <strong>how_to_extend_tvm</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="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>00:37.859</p></td>
+<td><p>00:38.111</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>00:02.297</p></td>
+<td><p>00:02.255</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>00:00.971</p></td>
+<td><p>00:00.957</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>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 0ad091624..a60b3a980 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: 6702us [6702us] (45.54%; 45.54%)
-FoldScaleAxis: 8016us [6us] (54.46%; 54.46%)
- FoldConstant: 8010us [1684us] (54.42%; 99.93%)
- InferType: 6326us [6326us] (42.98%; 78.97%)
+InferType: 6762us [6762us] (46.03%; 46.03%)
+FoldScaleAxis: 7930us [5us] (53.97%; 53.97%)
+ FoldConstant: 7925us [1655us] (53.94%; 99.94%)
+ InferType: 6270us [6270us] (42.67%; 79.12%)
</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: 6476us [6476us] (44.91%; 44.91%)
-FoldScaleAxis: 7946us [5us] (55.09%; 55.09%)
- FoldConstant: 7940us [1686us] (55.06%; 99.93%)
- InferType: 6254us [6254us] (43.37%; 78.77%)
+InferType: 6308us [6308us] (44.13%; 44.13%)
+FoldScaleAxis: 7986us [4us] (55.87%; 55.87%)
+ FoldConstant: 7982us [1638us] (55.84%; 99.94%)
+ InferType: 6344us [6344us] (44.38%; 79.48%)
</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 1b058a5b7..2af985895 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: 48.074004 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.227265 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 9995e9701..56801c278 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: 10.387367 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.538848 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 3018f1b6b..9ebcad795 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: 0.018712
-Baseline: 3.396784
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019083
+Baseline: 3.306953
</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: 0.300497
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296575
</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: 0.333640
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.328893
</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: 0.115574
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115053
</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: 0.109513
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111465
</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: 0.109566
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110850
</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: 0.145610
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146783
</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 5c3d5072f..19f118fde 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>00:34.391</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.152</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>00:32.139</p></td>
+<td><p>00:31.878</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>00:01.254</p></td>
+<td><p>00:01.226</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>00:00.998</p></td>
+<td><p>00:01.049</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 e55a1c021..65bd7492c 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>06:01.728</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:12.439</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>03:14.918</p></td>
+<td><p>03:26.775</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>01:21.922</p></td>
+<td><p>01:22.267</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>00:46.596</p></td>
+<td><p>00:46.794</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>00:20.916</p></td>
+<td><p>00:19.189</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.736</p></td>
+<td><p>00:08.838</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>00:08.640</p></td>
+<td><p>00:08.577</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 73ef052ec..03ac49d01 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
@@ -491,75 +491,959 @@ 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;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [288]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ 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[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 256) {
- let cse_var_1: int32 = (rc.outer.outer*18)
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[(threadIdx.x_1*9)] = 0f32
- pad_temp.shared_1[((threadIdx.x_1*9) + 1)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 2)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 3)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 5)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 4)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 4)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 5)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 3)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 6)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 2)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 7)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 9)*49)) + (floormod(threadIdx.x_1, 9)*7)) - 1)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*9) + 8)] = 0f32
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [288], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 6), 18))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 18))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 8), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 18)*4608)) + cse_var_1) + threadIdx.x_2) + 10)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 10), 27)) && (floormod((threadIdx.x_1 + 10), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 20), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + ((floordiv(threadIdx.x_1, 3) + 1)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 192), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 384), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 768), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 960), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1536), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1920), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2112), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2496), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3072), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3200), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3264), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3328), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3520), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3648), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3712), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3776), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3968), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4096), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4160), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4224), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4288), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4416), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4544), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4608)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4672)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4672), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4736)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4736), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4800)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4800), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4864)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4864), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4928)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4928), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 4992)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 4992), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5056)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5056), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5120)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5184)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5248)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5248), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5312)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5312), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5376), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5440)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5440), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5504)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5504), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5568)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5568), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5632)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5632), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5696)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5696), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5760)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5824)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5824), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5888)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5888), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 5952)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 5952), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6016)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6016), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6080)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6080), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6144)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6144), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6208)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6208), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6272), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6336)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6400)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6400), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6464)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6528)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6528), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6592)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6592), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6656)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6656), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6720)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6720), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6784)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6848)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6848), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6912)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 6976)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 6976), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7040)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7040), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7104)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7104), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7168), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7232)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7296)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7296), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7360)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7360), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7424)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7424), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7488)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7552)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7552), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7616)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7680)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7680), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7744)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7744), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7808)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7872)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7872), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 7936)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 7936), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8000)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8000), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8128)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8192)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8192), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8256)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8256), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8320)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8320), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8384)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8384), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8448)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8448), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8512)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8512), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8576)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8576), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8640)] = kernel[((((floordiv(blockIdx.x, 7)*589824) + cse_var_1) + threadIdx.x_2) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8704)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8704), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8768)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8768), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8832)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8832), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8896)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 8960), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 9024)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 9024), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 9088)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 9088), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 9152)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 9152), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (xx.outer.inner: int32, 0, 7) {
- let cse_var_2: int32 = (xx.outer.inner + 7)
- {
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 147)]))
- conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*18) + (rc.outer.inner*9)) + rx.outer.inner) + 150)]))
- }
- }
+ let cse_var_110: int32 = (rc.outer.inner*108)
+ let cse_var_109: int32 = (cse_var_110 + 99)
+ let cse_var_108: int32 = (cse_var_110 + 98)
+ let cse_var_107: int32 = (cse_var_110 + 97)
+ let cse_var_106: int32 = (cse_var_110 + 96)
+ let cse_var_105: int32 = (cse_var_110 + 95)
+ let cse_var_104: int32 = (cse_var_110 + 94)
+ let cse_var_103: int32 = (cse_var_110 + 93)
+ let cse_var_102: int32 = (cse_var_110 + 92)
+ let cse_var_101: int32 = (cse_var_110 + 91)
+ let cse_var_100: int32 = (cse_var_110 + 90)
+ let cse_var_99: int32 = (cse_var_110 + 9)
+ let cse_var_98: int32 = (cse_var_110 + 89)
+ let cse_var_97: int32 = (cse_var_110 + 88)
+ let cse_var_96: int32 = (cse_var_110 + 87)
+ let cse_var_95: int32 = (cse_var_110 + 86)
+ let cse_var_94: int32 = (cse_var_110 + 85)
+ let cse_var_93: int32 = (cse_var_110 + 84)
+ let cse_var_92: int32 = (cse_var_110 + 83)
+ let cse_var_91: int32 = (cse_var_110 + 82)
+ let cse_var_90: int32 = (cse_var_110 + 81)
+ let cse_var_89: int32 = (cse_var_110 + 80)
+ let cse_var_88: int32 = (cse_var_110 + 8)
+ let cse_var_87: int32 = (cse_var_110 + 79)
+ let cse_var_86: int32 = (cse_var_110 + 78)
+ let cse_var_85: int32 = (cse_var_110 + 77)
+ let cse_var_84: int32 = (cse_var_110 + 76)
+ let cse_var_83: int32 = (cse_var_110 + 75)
+ let cse_var_82: int32 = (cse_var_110 + 74)
+ let cse_var_81: int32 = (cse_var_110 + 73)
+ let cse_var_80: int32 = (cse_var_110 + 72)
+ let cse_var_79: int32 = (cse_var_110 + 71)
+ let cse_var_78: int32 = (cse_var_110 + 70)
+ let cse_var_77: int32 = (cse_var_110 + 7)
+ let cse_var_76: int32 = (cse_var_110 + 69)
+ let cse_var_75: int32 = (cse_var_110 + 68)
+ let cse_var_74: int32 = (cse_var_110 + 67)
+ let cse_var_73: int32 = (cse_var_110 + 66)
+ let cse_var_72: int32 = (cse_var_110 + 65)
+ let cse_var_71: int32 = (cse_var_110 + 64)
+ let cse_var_70: int32 = (cse_var_110 + 63)
+ let cse_var_69: int32 = (cse_var_110 + 62)
+ let cse_var_68: int32 = (cse_var_110 + 61)
+ let cse_var_67: int32 = (cse_var_110 + 60)
+ let cse_var_66: int32 = (cse_var_110 + 6)
+ let cse_var_65: int32 = (cse_var_110 + 59)
+ let cse_var_64: int32 = (cse_var_110 + 58)
+ let cse_var_63: int32 = (cse_var_110 + 57)
+ let cse_var_62: int32 = (cse_var_110 + 56)
+ let cse_var_61: int32 = (cse_var_110 + 55)
+ let cse_var_60: int32 = (cse_var_110 + 54)
+ let cse_var_59: int32 = (cse_var_110 + 53)
+ let cse_var_58: int32 = (cse_var_110 + 52)
+ let cse_var_57: int32 = (cse_var_110 + 51)
+ let cse_var_56: int32 = (cse_var_110 + 50)
+ let cse_var_55: int32 = (cse_var_110 + 5)
+ let cse_var_54: int32 = (cse_var_110 + 49)
+ let cse_var_53: int32 = (cse_var_110 + 48)
+ let cse_var_52: int32 = (cse_var_110 + 47)
+ let cse_var_51: int32 = (cse_var_110 + 46)
+ let cse_var_50: int32 = (cse_var_110 + 45)
+ let cse_var_49: int32 = (cse_var_110 + 44)
+ let cse_var_48: int32 = (cse_var_110 + 43)
+ let cse_var_47: int32 = (cse_var_110 + 42)
+ let cse_var_46: int32 = (cse_var_110 + 41)
+ let cse_var_45: int32 = (cse_var_110 + 40)
+ let cse_var_44: int32 = (cse_var_110 + 4)
+ let cse_var_43: int32 = (cse_var_110 + 39)
+ let cse_var_42: int32 = (cse_var_110 + 38)
+ let cse_var_41: int32 = (cse_var_110 + 37)
+ let cse_var_40: int32 = (cse_var_110 + 36)
+ let cse_var_39: int32 = (cse_var_110 + 35)
+ let cse_var_38: int32 = (cse_var_110 + 34)
+ let cse_var_37: int32 = (cse_var_110 + 33)
+ let cse_var_36: int32 = (cse_var_110 + 32)
+ let cse_var_35: int32 = (cse_var_110 + 31)
+ let cse_var_34: int32 = (cse_var_110 + 30)
+ let cse_var_33: int32 = (cse_var_110 + 3)
+ let cse_var_32: int32 = (cse_var_110 + 29)
+ let cse_var_31: int32 = (cse_var_110 + 28)
+ let cse_var_30: int32 = (cse_var_110 + 27)
+ let cse_var_29: int32 = (cse_var_110 + 26)
+ let cse_var_28: int32 = (cse_var_110 + 25)
+ let cse_var_27: int32 = (cse_var_110 + 24)
+ let cse_var_26: int32 = (cse_var_110 + 23)
+ let cse_var_25: int32 = (cse_var_110 + 22)
+ let cse_var_24: int32 = (cse_var_110 + 21)
+ let cse_var_23: int32 = (cse_var_110 + 20)
+ let cse_var_22: int32 = (cse_var_110 + 2)
+ let cse_var_21: int32 = (cse_var_110 + 19)
+ let cse_var_20: int32 = (cse_var_110 + 18)
+ let cse_var_19: int32 = (cse_var_110 + 17)
+ let cse_var_18: int32 = (cse_var_110 + 16)
+ let cse_var_17: int32 = (cse_var_110 + 15)
+ let cse_var_16: int32 = (cse_var_110 + 14)
+ let cse_var_15: int32 = (cse_var_110 + 13)
+ let cse_var_14: int32 = (cse_var_110 + 12)
+ let cse_var_13: int32 = (cse_var_110 + 11)
+ let cse_var_12: int32 = (cse_var_110 + 107)
+ let cse_var_11: int32 = (cse_var_110 + 106)
+ let cse_var_10: int32 = (cse_var_110 + 105)
+ let cse_var_9: int32 = (cse_var_110 + 104)
+ let cse_var_8: int32 = (cse_var_110 + 103)
+ let cse_var_7: int32 = (cse_var_110 + 102)
+ let cse_var_6: int32 = (cse_var_110 + 101)
+ let cse_var_5: int32 = (cse_var_110 + 100)
+ let cse_var_4: int32 = (cse_var_110 + 10)
+ let cse_var_3: int32 = (cse_var_110 + 1)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_110]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4608)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_33]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4611)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_66]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_99]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4614)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_30]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4617)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_34]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4620)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_37]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_40]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_43]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_47]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_50]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_53]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_57]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4623)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_60]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4626)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_63]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4629)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_67]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_70]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_73]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_76]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_80]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_83]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_86]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4632)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_90]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4635)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_93]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4638)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_96]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_100]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_103]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_106]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_109]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4641)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4609)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_44]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4612)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_77]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4615)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_31]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4618)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_35]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4621)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_38]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_41]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_45]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_48]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_51]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_54]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_58]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4624)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_61]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4627)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_64]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4630)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_68]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_71]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_74]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_78]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_81]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_84]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_87]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4633)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_91]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4636)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_94]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4639)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_97]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_101]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_104]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_107]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4642)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4610)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_55]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4613)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_88]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4616)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_32]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4619)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_36]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4622)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_39]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_42]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_46]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_49]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_52]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_56]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_59]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4625)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_62]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4628)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_65]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4631)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_69]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_72]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_75]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_79]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_82]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_85]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_89]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4634)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_92]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4637)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_95]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4640)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_98]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_102]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_105]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_108]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*36)) + 4643)]))
}
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner) + 392)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias[(((blockIdx.x*16) + floordiv(threadIdx.x, 7)) + 8)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3136)] = max((conv2d_nchw_1[7] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3143)] = max((conv2d_nchw_1[8] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3150)] = max((conv2d_nchw_1[9] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3157)] = max((conv2d_nchw_1[10] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3164)] = max((conv2d_nchw_1[11] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3171)] = max((conv2d_nchw_1[12] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 3178)] = max((conv2d_nchw_1[13] + bias[(((floordiv(blockIdx.x, 7)*128) + threadIdx.x) + 64)]), 0f32)
}
}
</pre></div>
@@ -595,7 +1479,7 @@ 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: 0.249 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.300 ms
</pre></div>
</div>
</div>
@@ -626,17 +1510,17 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_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_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
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_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
-conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_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=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=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=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)
@@ -647,12 +1531,12 @@ compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
-compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
+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=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
@@ -673,14 +1557,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=9)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -698,63 +1582,698 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[162];
- __shared__ float kernel_shared[288];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[9216];
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[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 9)] = 0.000000e+00f;
- pad_temp_shared[((((int)threadIdx.x) * 9) + 1)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 2)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 3)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 5)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 4)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 4)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 5)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 3)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 6)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 2)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 7)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) - 1)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 9) + 8)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
- if (((int)threadIdx.x) < 8) {
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 10)];
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((3 <= ((((int)threadIdx.x) + 10) % 27)) && (((((int)threadIdx.x) + 10) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ if (((int)threadIdx.x) < 24) {
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = ((((((int)threadIdx.x) < 21) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 1)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4608)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 4672)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4736)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4736) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4800)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4800) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4864)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4864) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4992)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5056)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5056) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5120)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5184)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 5248)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5312)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5312) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5376) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5440)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5440) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5504)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5568)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5632)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5696)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5760)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5824) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5888)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5888) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 5952)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5952) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6016)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6016) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6080)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6144)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6208)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6336)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 6400)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6464)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6464) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6528)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6528) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6592)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6592) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6656)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6720) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6784)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6848)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 6912)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 6976)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6976) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7040)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7040) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7104)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7104) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7232)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7296)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7360)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7424)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7488)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 7552)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7552) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7680)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7744)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7744) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7808)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7872)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7872) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 7936)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8000)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 8128)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8192)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8256)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8320)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8384)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8448)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8576)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8576) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8640)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 8704)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8768)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8832)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8896)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 9024)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 9088)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9088) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 9152)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9152) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 144)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 3)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 147)]));
- conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 6)]));
- conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((((rc_outer_inner * 81) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 18) + (rc_outer_inner * 9)) + rx_outer_inner) + 150)]));
- }
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rc_outer_inner * 108)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 36))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rc_outer_inner * 108)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4608)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4611)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4614)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4617)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 30)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4620)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 33)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 36)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 39)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 42)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 45)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 48)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 51)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4623)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 54)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 54)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4626)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 57)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4629)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 78)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 60)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 63)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 66)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 69)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 72)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 75)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 78)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4632)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 81)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 81)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4635)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 84)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4638)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 105)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 87)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 90)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 93)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 96)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 99)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 102)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 105)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4641)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4609)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4612)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4615)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 28)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4618)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 31)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4621)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 34)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 37)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 40)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 43)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 46)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 49)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 52)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4624)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 55)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 55)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4627)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 58)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4630)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 79)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 61)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 64)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 67)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 70)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 73)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 76)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 79)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4633)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 82)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 82)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4636)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 85)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4639)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 106)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 88)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 91)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 94)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 97)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 100)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 103)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 106)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4642)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4610)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4613)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4616)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 29)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4619)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 32)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4622)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 35)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 38)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 41)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 44)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 47)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 50)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 53)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4625)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 56)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 56)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4628)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 59)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4631)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 80)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 62)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 65)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 68)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 71)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 74)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 77)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 80)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4634)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 83)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 83)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4637)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 86)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4640)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 108) + 107)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 108) + 89)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 108) + 92)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 108) + 95)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 108) + 98)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 108) + 101)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 108) + 104)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 108) + 107)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 36)) + 4643)]));
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner) + 392)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3136)] = max((conv2d_nchw[7] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3143)] = max((conv2d_nchw[8] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3150)] = max((conv2d_nchw[9] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3157)] = max((conv2d_nchw[10] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3164)] = max((conv2d_nchw[11] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3171)] = max((conv2d_nchw[12] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 3178)] = max((conv2d_nchw[13] + bias[((((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x)) + 64)]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -790,7 +2309,7 @@ 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 14.918 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 26.775 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 bd6641d1a..3c67b43d2 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)
- 10.1906 10.2254 10.2505 10.0959 0.0678
+ 9.8669 9.8798 9.8946 9.8263 0.0293
</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 cbf06d959..5dfcd1722 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)
- 751.5250 751.2559 752.9956 750.3234 1.1074
+ 763.3407 762.9830 764.3289 762.7103 0.7075
</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 21.922 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.267 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 0f251f703..c8b87f932 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,29 +625,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (nb_j.inner: int32, 0, 2) {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
for (i.inner.init: int32, 0, 4) {
for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [128], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
for (i.inner: int32, 0, 4) {
for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 4) {
- let cse_var_4: int32 = (((i0.outer*2048) + (i0.inner*512)) + (i1.outer*32))
- compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -685,7 +686,7 @@ 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: 1.235 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.452 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 79f4295d3..66c07e07a 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>00:46.359</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.017</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>00:46.324</p></td>
+<td><p>00:45.981</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>
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 55c887220..fc9ae34bd 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: 188.85/188.85 result: MeasureResult(costs=(0.0012258750111111111,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0600717067718506, timestamp=1661223828.9150054) [('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: 0.00/188.85 result: Traceback (most recent call last):
+No: 9 GFLOPS: 80.73/80.73 result: MeasureResult(costs=(0.002867500257142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8834233283996582, timestamp=1661244463.0365772) [('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: 0.00/80.73 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: 260.69/260.69 result: MeasureResult(costs=(0.0008880194309392265,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.669468641281128, timestamp=1661223829.818118) [('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: 0.00/260.69 result: Traceback (most recent call last):
+No: 11 GFLOPS: 261.00/261.00 result: MeasureResult(costs=(0.0008869873701657459,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4214684963226318, timestamp=1661244463.8954568) [('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: 0.00/261.00 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: 0.00/260.69 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/261.00 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: 0.00/260.69 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/261.00 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: 5.26/260.69 result: MeasureResult(costs=(0.04400975375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8418543338775635, timestamp=1661223834.3559484) [('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: 3.35/260.69 result: MeasureResult(costs=(0.06910109149999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.501275300979614, timestamp=1661223835.5905685) [('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: 0.00/260.69 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.49/261.00 result: MeasureResult(costs=(0.04217780425,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8148174285888672, timestamp=1661244468.4581046) [('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: 3.34/261.00 result: MeasureResult(costs=(0.06938481925000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.559957504272461, timestamp=1661244469.704005) [('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: 0.00/261.00 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: 0.00/260.69 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: 28.07/260.69 result: MeasureResult(costs=(0.008247764857142858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3089728355407715, timestamp=1661223846.6293054) [('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: 0.00/260.69 result: Traceback (most recent call last):
+No: 18 GFLOPS: 25.97/261.00 result: MeasureResult(costs=(0.008912912,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1464619636535645, timestamp=1661244480.6022627) [('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: 0.00/261.00 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: 0.00/260.69 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/261.00 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: 0.001277
+Time cost of this operator: 0.001254
</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 ba3f14250..f4a2e90cc 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 304.2 98.701 (1, 2, 10, 10, 3) 2 1 [304.2]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.053 0.99 (1, 6, 10, 10) 1 1 [3.053]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.309 (1, 1, 10, 10, 3) 1 1 [0.952]
-Total_time - 308.205 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.0 98.731 (1, 2, 10, 10, 3) 2 1 [311.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.03 0.962 (1, 6, 10, 10) 1 1 [3.03]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.307 (1, 1, 10, 10, 3) 1 1 [0.968]
+Total_time - 314.998 - - - - -
</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 195.8 98.676 (1, 6, 10, 10, 1) 2 1 [195.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.78 0.897 (1, 6, 10, 10) 1 1 [1.78]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.847 0.427 (1, 3, 10, 10, 1) 1 1 [0.847]
-Total_time - 198.427 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.375 96.71 (1, 6, 10, 10, 1) 2 1 [80.375]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.775 2.136 (1, 6, 10, 10) 1 1 [1.775]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.959 1.154 (1, 1, 10, 10, 3) 1 1 [0.959]
+Total_time - 83.109 - - - - -
</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 807c442fa..8a9f52299 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/tmp9gq1s984/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpanpuckf6/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/tmp9gq1s984/images/target contains 8144 images
-/tmp/tmp9gq1s984/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/tmpanpuckf6/images/target contains 8144 images
+/tmp/tmpanpuckf6/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 - 54s - loss: 0.2070 - accuracy: 0.9267 - val_loss: 0.1239 - val_accuracy: 0.9592
+328/328 - 55s - loss: 0.2198 - accuracy: 0.9231 - val_loss: 0.1355 - val_accuracy: 0.9607
Epoch 2/3
-328/328 - 52s - loss: 0.0938 - accuracy: 0.9656 - val_loss: 0.1060 - val_accuracy: 0.9668
+328/328 - 52s - loss: 0.0979 - accuracy: 0.9637 - val_loss: 0.1210 - val_accuracy: 0.9645
Epoch 3/3
-328/328 - 52s - loss: 0.0605 - accuracy: 0.9767 - val_loss: 0.1311 - val_accuracy: 0.9603
+328/328 - 52s - loss: 0.0685 - accuracy: 0.9743 - val_loss: 0.1145 - val_accuracy: 0.9649
-<keras.callbacks.History object at 0x7f3ca86d5110>
+<keras.callbacks.History object at 0x7f6cad2dfb90>
</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 6.391 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 55.340 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 e8c3dd2ec..a29e5de27 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>05:59.437</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:48.653</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>05:06.391</p></td>
+<td><p>04:55.340</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>00:42.046</p></td>
+<td><p>00:41.994</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>00:07.803</p></td>
+<td><p>00:08.042</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>00:03.195</p></td>
+<td><p>00:03.275</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 f63bcecf1..c43504e4b 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>00:41.650</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.745</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>00:30.651</p></td>
+<td><p>00:31.312</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>00:09.658</p></td>
+<td><p>00:09.889</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>00:01.335</p></td>
+<td><p>00:01.538</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 2c8838ad8..043f6bf1b 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 0x7f3c149bd170>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f6c375d90e0>
</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 902805d7c..ac03a31d3 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>00:03.886</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.227</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>00:01.818</p></td>
+<td><p>00:01.947</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>00:00.870</p></td>
+<td><p>00:01.026</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>00:00.510</p></td>
+<td><p>00:00.542</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>00:00.500</p></td>
+<td><p>00:00.528</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>00:00.105</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index cbc431fb4..987022bdb 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/tmp3_98ccsz/input0.cc'\nsource_filename = \"/tmp/tmp3_98ccsz/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/tmp_d_uffj2/input0.cc'\nsource_filename = \"/tmp/tmp_d_uffj2/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 3153785d7..aa2238b85 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,7 +224,17 @@
<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"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<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="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 4df07f743..da636e15e 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 2fe7ed4e7..3117c4ed6 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/58f2139ff/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 13c3b8020..7f49aa03d 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/58f2139ff/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 55059b31c..fa84f9353 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/58f2139ff/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 905988674..aff6f5876 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/58f2139ff/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 212be17c2..66a740bbd 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/58f2139ff/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 46b4b842d..2f47d1840 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/58f2139ff/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 97a235d22..6cbbee05b 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/58f2139ff/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 1e7c9efbc..7d32d1c7a 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/58f2139ff/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/web/src/runtime.ts#L1145">runtime.ts:1145</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/58f2139ff/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 117902372..816abc0cf 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/58f2139ff/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 332b55731..11a85d49f 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/58f2139ff/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 0f12fb42a..84c11d712 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/58f2139ff/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 56fe214e8..3ceb93a0d 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/58f2139ff/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 829ab4e78..97996e89b 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/58f2139ff/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 9d5fcc2b4..fd71b6037 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/58f2139ff/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 621ff84e4..71914a431 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/58f2139ff/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 0152a3968..7968f7d46 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/58f2139ff/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 7c5338854..6d9dfed2b 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/58f2139ff/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 e848a99a3..a890b6694 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/58f2139ff/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 3b84f04b2..b37cc8a1c 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/58f2139ff/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 ff92f9613..2b53982c6 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/58f2139ff/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 f393b7faf..556eb44b4 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/58f2139ff/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/web/src/runtime.ts#L1367">runtime.ts:1367</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/58f2139ff/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 b368300f6..dd44106d7 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/58f2139ff/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 525d5315b..e66eddae6 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/58f2139ff/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 9ca6da8b8..59e74cb46 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/58f2139ff/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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/58f2139ff/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/383bd4193/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 79b918125..59cb79229 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 122f675c6..469cbf637 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>00:21.406</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.053</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>00:21.399</p></td>
+<td><p>00:21.046</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 b1da00f64..3d9142277 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 22.88s!
+resnet18_v1 inference graph built in 22.86s!
</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 f27425238..a3d21ba38 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 15.87s!
+yolov3-tiny inference graph built in 16.10s!
</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 bd3f5cb74..5f454b810 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>01:31.096</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:32.017</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>00:48.287</p></td>
+<td><p>00:48.772</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>00:42.809</p></td>
+<td><p>00:43.246</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 3e88be486..121806d5a 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>00:03.201</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.385</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>00:02.813</p></td>
+<td><p>00:02.971</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>00:00.388</p></td>
+<td><p>00:00.414</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 8886185a7..bdb615a74 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>00:00.696</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.771</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>00:00.402</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>00:00.321</p></td>
+<td><p>00:00.369</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 122332b5f..723b8f05f 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -567,7 +567,7 @@ 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: 92.551 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.568 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index de8b0dbaf..077461d74 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ 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: 10.72/10.72 result: MeasureResult(costs=(0.0250505048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5350730419158936, timestamp=1661222640.539018) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.91/10.72 result: MeasureResult(costs=(0.0922622846,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6240155696868896, timestamp=1661222642.1854763) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.95/11.95 result: MeasureResult(costs=(0.022465997600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5506978034973145, timestamp=1661222643.2433298) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.78/11.95 result: MeasureResult(costs=(0.15057060100000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5330920219421387, timestamp=1661222646.346556) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.76/11.95 result: MeasureResult(costs=(0.07148399799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2783560752868652, timestamp=1661222647.755876) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.80/11.95 result: MeasureResult(costs=(0.1489843268,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.551570177078247, timestamp=1661222650.3522766) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.88/11.95 result: MeasureResult(costs=(0.305054975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.998769998550415, timestamp=1661222655.9184394) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.54/11.95 result: MeasureResult(costs=(0.025462705000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5463662147521973, timestamp=1661222656.4874182) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.75/11.95 result: MeasureResult(costs=(0.1531640826,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.549555540084839, timestamp=1661222659.1571317) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.44/11.95 result: MeasureResult(costs=(0.10983492819999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.859569787979126, timestamp=1661222661.0761063) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.58/9.58 result: MeasureResult(costs=(0.028032059400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5825996398925781, timestamp=1661243257.8703933) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.72/9.58 result: MeasureResult(costs=(0.0986421146,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7145910263061523, timestamp=1661243259.6102347) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.84/11.84 result: MeasureResult(costs=(0.022672648799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5500392913818359, timestamp=1661243260.6846845) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.57/11.84 result: MeasureResult(costs=(0.1708475746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.859412670135498, timestamp=1661243264.108421) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.70/11.84 result: MeasureResult(costs=(0.0724912362,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3039016723632812, timestamp=1661243265.537487) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.83/11.84 result: MeasureResult(costs=(0.1468703952,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5044596195220947, timestamp=1661243268.0899267) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.88/11.84 result: MeasureResult(costs=(0.3063590632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.021007537841797, timestamp=1661243273.690963) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.40/11.84 result: MeasureResult(costs=(0.0258117624,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5625371932983398, timestamp=1661243274.265915) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.58/11.84 result: MeasureResult(costs=(0.1703779124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8350937366485596, timestamp=1661243277.2198384) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.77/11.84 result: MeasureResult(costs=(0.0968355918,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6580238342285156, timestamp=1661243278.930646) [('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 3326ded4c..406d0dc84 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ 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': 492.48641366999436, 'median': 492.1965809500307, 'std': 0.8522537710826755}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 491.82149348000166, 'median': 491.77043189997676, 'std': 1.0117483041688307}
</pre></div>
</div>
</div>
@@ -706,178 +706,178 @@ 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) | 6.27 s
-[Task 1/25] Current/Best: 6.16/ 17.55 GFLOPS | Progress: (8/20) | 9.19 s
-[Task 1/25] Current/Best: 11.55/ 22.71 GFLOPS | Progress: (12/20) | 11.62 s
-[Task 1/25] Current/Best: 16.43/ 22.71 GFLOPS | Progress: (16/20) | 13.30 s
-[Task 1/25] Current/Best: 11.63/ 23.81 GFLOPS | Progress: (20/20) | 15.05 s Done.
+[Task 1/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (4/20) | 6.35 s
+[Task 1/25] Current/Best: 6.15/ 17.51 GFLOPS | Progress: (8/20) | 9.32 s
+[Task 1/25] Current/Best: 11.52/ 22.77 GFLOPS | Progress: (12/20) | 11.74 s
+[Task 1/25] Current/Best: 16.55/ 22.77 GFLOPS | Progress: (16/20) | 13.43 s
+[Task 1/25] Current/Best: 11.62/ 23.82 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: 12.10/ 12.95 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 2/25] Current/Best: 13.92/ 18.66 GFLOPS | Progress: (8/20) | 4.94 s
-[Task 2/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (12/20) | 6.30 s
-[Task 2/25] Current/Best: 12.55/ 21.10 GFLOPS | Progress: (16/20) | 7.57 s
-[Task 2/25] Current/Best: 19.35/ 21.10 GFLOPS | Progress: (20/20) | 9.11 s Done.
+[Task 2/25] Current/Best: 12.34/ 13.08 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 2/25] Current/Best: 14.15/ 18.66 GFLOPS | Progress: (8/20) | 5.12 s
+[Task 2/25] Current/Best: 21.05/ 21.05 GFLOPS | Progress: (12/20) | 6.44 s
+[Task 2/25] Current/Best: 12.19/ 21.05 GFLOPS | Progress: (16/20) | 7.68 s
+[Task 2/25] Current/Best: 19.48/ 21.05 GFLOPS | Progress: (20/20) | 9.29 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/ 10.84 GFLOPS | Progress: (4/20) | 5.87 s
-[Task 3/25] Current/Best: 15.55/ 16.80 GFLOPS | Progress: (8/20) | 7.78 s
-[Task 3/25] Current/Best: 15.24/ 16.80 GFLOPS | Progress: (12/20) | 9.50 s
-[Task 3/25] Current/Best: 7.29/ 24.03 GFLOPS | Progress: (16/20) | 11.44 s
-[Task 3/25] Current/Best: 12.28/ 24.03 GFLOPS | Progress: (20/20) | 15.98 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.82 GFLOPS | Progress: (4/20) | 5.86 s
+[Task 3/25] Current/Best: 15.28/ 16.78 GFLOPS | Progress: (8/20) | 7.79 s
+[Task 3/25] Current/Best: 14.99/ 16.78 GFLOPS | Progress: (12/20) | 9.49 s
+[Task 3/25] Current/Best: 7.22/ 23.63 GFLOPS | Progress: (16/20) | 11.44 s
+[Task 3/25] Current/Best: 12.59/ 23.63 GFLOPS | Progress: (20/20) | 15.93 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.66/ 20.64 GFLOPS | Progress: (4/20) | 2.39 s
-[Task 4/25] Current/Best: 6.84/ 20.64 GFLOPS | Progress: (8/20) | 6.70 s
-[Task 4/25] Current/Best: 22.22/ 22.22 GFLOPS | Progress: (12/20) | 11.14 s
-[Task 4/25] Current/Best: 17.29/ 22.22 GFLOPS | Progress: (16/20) | 13.39 s
-[Task 4/25] Current/Best: 13.36/ 22.22 GFLOPS | Progress: (20/20) | 15.41 s Done.
+[Task 4/25] Current/Best: 9.57/ 20.53 GFLOPS | Progress: (4/20) | 2.39 s
+[Task 4/25] Current/Best: 6.86/ 20.53 GFLOPS | Progress: (8/20) | 6.70 s
+[Task 4/25] Current/Best: 22.47/ 22.47 GFLOPS | Progress: (12/20) | 11.23 s
+[Task 4/25] Current/Best: 17.41/ 22.47 GFLOPS | Progress: (16/20) | 13.43 s
+[Task 4/25] Current/Best: 13.48/ 22.47 GFLOPS | Progress: (20/20) | 15.41 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.77/ 10.40 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 5/25] Current/Best: 11.72/ 12.76 GFLOPS | Progress: (8/20) | 4.68 s
-[Task 5/25] Current/Best: 11.28/ 18.03 GFLOPS | Progress: (12/20) | 7.64 s
-[Task 5/25] Current/Best: 11.95/ 22.72 GFLOPS | Progress: (16/20) | 9.05 s
-[Task 5/25] Current/Best: 11.92/ 22.72 GFLOPS | Progress: (20/20) | 10.91 s Done.
+[Task 5/25] Current/Best: 9.73/ 10.45 GFLOPS | Progress: (4/20) | 2.62 s
+[Task 5/25] Current/Best: 11.75/ 12.87 GFLOPS | Progress: (8/20) | 4.70 s
+[Task 5/25] Current/Best: 11.54/ 18.03 GFLOPS | Progress: (12/20) | 7.78 s
+[Task 5/25] Current/Best: 11.80/ 22.46 GFLOPS | Progress: (16/20) | 9.19 s
+[Task 5/25] Current/Best: 12.07/ 22.46 GFLOPS | Progress: (20/20) | 11.02 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.28/ 20.64 GFLOPS | Progress: (4/20) | 3.97 s
-[Task 6/25] Current/Best: 19.02/ 20.64 GFLOPS | Progress: (8/20) | 5.73 s
-[Task 6/25] Current/Best: 13.29/ 20.64 GFLOPS | Progress: (12/20) | 7.65 s
-[Task 6/25] Current/Best: 19.81/ 20.64 GFLOPS | Progress: (16/20) | 9.93 s
-[Task 6/25] Current/Best: 3.76/ 20.64 GFLOPS | Progress: (20/20) | 12.47 s Done.
+[Task 6/25] Current/Best: 12.18/ 20.70 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 6/25] Current/Best: 18.98/ 20.70 GFLOPS | Progress: (8/20) | 5.75 s
+[Task 6/25] Current/Best: 13.27/ 20.70 GFLOPS | Progress: (12/20) | 7.67 s
+[Task 6/25] Current/Best: 19.91/ 20.70 GFLOPS | Progress: (16/20) | 9.92 s
+[Task 6/25] Current/Best: 3.73/ 20.70 GFLOPS | Progress: (20/20) | 12.44 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.07/ 12.86 GFLOPS | Progress: (4/20) | 3.68 s
-[Task 7/25] Current/Best: 20.34/ 21.09 GFLOPS | Progress: (8/20) | 5.20 s
-[Task 7/25] Current/Best: 15.91/ 21.09 GFLOPS | Progress: (12/20) | 7.11 s
-[Task 7/25] Current/Best: 12.23/ 21.09 GFLOPS | Progress: (16/20) | 9.16 s
-[Task 7/25] Current/Best: 6.30/ 21.75 GFLOPS | Progress: (20/20) | 11.62 s Done.
+[Task 7/25] Current/Best: 11.17/ 12.96 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 7/25] Current/Best: 20.36/ 21.08 GFLOPS | Progress: (8/20) | 5.14 s
+[Task 7/25] Current/Best: 15.90/ 21.08 GFLOPS | Progress: (12/20) | 7.04 s
+[Task 7/25] Current/Best: 12.26/ 21.08 GFLOPS | Progress: (16/20) | 9.07 s
+[Task 7/25] Current/Best: 6.36/ 21.82 GFLOPS | Progress: (20/20) | 11.52 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.91/ 14.06 GFLOPS | Progress: (4/20) | 2.95 s
-[Task 8/25] Current/Best: 9.39/ 14.06 GFLOPS | Progress: (8/20) | 7.71 s
-[Task 8/25] Current/Best: 12.46/ 14.06 GFLOPS | Progress: (12/20) | 13.82 s
-[Task 8/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (16/20) | 15.91 s
-[Task 8/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (20/20) | 22.36 s Done.
+[Task 8/25] Current/Best: 9.90/ 14.20 GFLOPS | Progress: (4/20) | 2.90 s
+[Task 8/25] Current/Best: 9.44/ 14.20 GFLOPS | Progress: (8/20) | 7.63 s
+[Task 8/25] Current/Best: 12.36/ 14.20 GFLOPS | Progress: (12/20) | 13.75 s
+[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (16/20) | 15.87 s
+[Task 8/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (20/20) | 22.31 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/ 15.89 GFLOPS | Progress: (4/20) | 11.98 s
-[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.73 s
-[Task 9/25] Current/Best: 8.26/ 23.47 GFLOPS | Progress: (12/20) | 16.07 s
-[Task 9/25] Current/Best: 17.98/ 23.47 GFLOPS | Progress: (16/20) | 18.60 s
-[Task 9/25] Current/Best: 9.19/ 23.47 GFLOPS | Progress: (20/20) | 26.08 s
+[Task 9/25] Current/Best: 14.31/ 15.72 GFLOPS | Progress: (4/20) | 12.00 s
+[Task 9/25] Current/Best: 23.59/ 23.59 GFLOPS | Progress: (8/20) | 13.80 s
+[Task 9/25] Current/Best: 8.24/ 23.59 GFLOPS | Progress: (12/20) | 16.17 s
+[Task 9/25] Current/Best: 18.04/ 23.59 GFLOPS | Progress: (16/20) | 18.81 s
+[Task 9/25] Current/Best: 9.20/ 23.59 GFLOPS | Progress: (20/20) | 26.48 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (4/20) | 2.59 s
-[Task 10/25] Current/Best: 15.57/ 18.25 GFLOPS | Progress: (8/20) | 4.17 s
-[Task 10/25] Current/Best: 12.25/ 18.96 GFLOPS | Progress: (12/20) | 5.69 s
-[Task 10/25] Current/Best: 19.10/ 20.33 GFLOPS | Progress: (16/20) | 6.80 s
-[Task 10/25] Current/Best: 8.95/ 20.33 GFLOPS | Progress: (20/20) | 8.33 s Done.
+[Task 10/25] Current/Best: 18.29/ 18.29 GFLOPS | Progress: (4/20) | 2.58 s
+[Task 10/25] Current/Best: 15.40/ 18.29 GFLOPS | Progress: (8/20) | 4.18 s
+[Task 10/25] Current/Best: 12.63/ 18.95 GFLOPS | Progress: (12/20) | 5.71 s
+[Task 10/25] Current/Best: 19.12/ 20.37 GFLOPS | Progress: (16/20) | 6.82 s
+[Task 10/25] Current/Best: 8.87/ 20.37 GFLOPS | Progress: (20/20) | 8.35 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.09/ 18.16 GFLOPS | Progress: (4/20) | 3.33 s
-[Task 11/25] Current/Best: 15.03/ 18.16 GFLOPS | Progress: (8/20) | 6.06 s
-[Task 11/25] Current/Best: 18.08/ 18.16 GFLOPS | Progress: (12/20) | 8.12 s
-[Task 11/25] Current/Best: 13.47/ 20.89 GFLOPS | Progress: (16/20) | 10.89 s
-[Task 11/25] Current/Best: 19.46/ 21.57 GFLOPS | Progress: (20/20) | 12.90 s Done.
+[Task 11/25] Current/Best: 12.30/ 18.09 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 11/25] Current/Best: 16.84/ 18.09 GFLOPS | Progress: (8/20) | 6.01 s
+[Task 11/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (12/20) | 8.07 s
+[Task 11/25] Current/Best: 13.44/ 21.02 GFLOPS | Progress: (16/20) | 10.83 s
+[Task 11/25] Current/Best: 19.50/ 21.64 GFLOPS | Progress: (20/20) | 12.85 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.81/ 18.03 GFLOPS | Progress: (4/20) | 5.37 s
-[Task 12/25] Current/Best: 5.30/ 18.03 GFLOPS | Progress: (8/20) | 9.05 s
-[Task 12/25] Current/Best: 18.74/ 18.87 GFLOPS | Progress: (12/20) | 11.04 s
-[Task 12/25] Current/Best: 15.52/ 18.87 GFLOPS | Progress: (16/20) | 13.77 s
-[Task 12/25] Current/Best: 15.10/ 18.87 GFLOPS | Progress: (20/20) | 15.69 s Done.
+[Task 12/25] Current/Best: 7.81/ 18.07 GFLOPS | Progress: (4/20) | 5.38 s
+[Task 12/25] Current/Best: 5.26/ 18.07 GFLOPS | Progress: (8/20) | 9.09 s
+[Task 12/25] Current/Best: 18.99/ 18.99 GFLOPS | Progress: (12/20) | 11.08 s
+[Task 12/25] Current/Best: 15.48/ 18.99 GFLOPS | Progress: (16/20) | 13.87 s
+[Task 12/25] Current/Best: 15.18/ 18.99 GFLOPS | Progress: (20/20) | 15.82 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.70/ 17.40 GFLOPS | Progress: (4/20) | 3.65 s
-[Task 13/25] Current/Best: 15.94/ 20.97 GFLOPS | Progress: (8/20) | 6.08 s
-[Task 13/25] Current/Best: 19.61/ 21.88 GFLOPS | Progress: (12/20) | 8.99 s
-[Task 13/25] Current/Best: 12.28/ 21.88 GFLOPS | Progress: (16/20) | 12.36 s
-[Task 13/25] Current/Best: 18.95/ 21.88 GFLOPS | Progress: (20/20) | 14.60 s Done.
+[Task 13/25] Current/Best: 8.47/ 17.29 GFLOPS | Progress: (4/20) | 3.73 s
+[Task 13/25] Current/Best: 15.66/ 20.92 GFLOPS | Progress: (8/20) | 6.15 s
+[Task 13/25] Current/Best: 19.51/ 21.56 GFLOPS | Progress: (12/20) | 9.01 s
+[Task 13/25] Current/Best: 12.30/ 21.56 GFLOPS | Progress: (16/20) | 12.42 s
+[Task 13/25] Current/Best: 18.60/ 21.56 GFLOPS | Progress: (20/20) | 14.72 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.69/ 13.69 GFLOPS | Progress: (4/20) | 3.33 s
-[Task 14/25] Current/Best: 6.19/ 13.69 GFLOPS | Progress: (8/20) | 5.51 s
-[Task 14/25] Current/Best: 20.24/ 20.24 GFLOPS | Progress: (12/20) | 8.05 s
-[Task 14/25] Current/Best: 16.64/ 20.24 GFLOPS | Progress: (16/20) | 9.73 s Done.
+[Task 14/25] Current/Best: 13.66/ 13.66 GFLOPS | Progress: (4/20) | 3.34 s
+[Task 14/25] Current/Best: 6.10/ 13.66 GFLOPS | Progress: (8/20) | 5.54 s
+[Task 14/25] Current/Best: 20.27/ 20.27 GFLOPS | Progress: (12/20) | 8.06 s
+[Task 14/25] Current/Best: 16.87/ 20.27 GFLOPS | Progress: (16/20) | 9.70 s Done.
-[Task 14/25] Current/Best: 17.45/ 20.24 GFLOPS | Progress: (20/20) | 11.48 s
+[Task 14/25] Current/Best: 17.00/ 20.27 GFLOPS | Progress: (20/20) | 11.53 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.42/ 17.82 GFLOPS | Progress: (4/20) | 2.74 s
-[Task 15/25] Current/Best: 14.59/ 18.26 GFLOPS | Progress: (8/20) | 4.07 s
-[Task 15/25] Current/Best: 10.46/ 22.53 GFLOPS | Progress: (12/20) | 6.13 s
-[Task 15/25] Current/Best: 20.70/ 22.53 GFLOPS | Progress: (16/20) | 9.13 s
-[Task 15/25] Current/Best: 9.82/ 22.53 GFLOPS | Progress: (20/20) | 10.10 s
+[Task 15/25] Current/Best: 16.16/ 17.59 GFLOPS | Progress: (4/20) | 2.76 s
+[Task 15/25] Current/Best: 14.26/ 17.97 GFLOPS | Progress: (8/20) | 4.06 s
+[Task 15/25] Current/Best: 10.39/ 22.26 GFLOPS | Progress: (12/20) | 6.17 s
+[Task 15/25] Current/Best: 20.39/ 22.26 GFLOPS | Progress: (16/20) | 9.01 s
+[Task 15/25] Current/Best: 9.71/ 22.26 GFLOPS | Progress: (20/20) | 9.99 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (4/20) | 2.94 s
-[Task 16/25] Current/Best: 3.07/ 20.74 GFLOPS | Progress: (8/20) | 4.54 s
-[Task 16/25] Current/Best: 19.82/ 20.74 GFLOPS | Progress: (12/20) | 5.75 s
-[Task 16/25] Current/Best: 17.76/ 20.74 GFLOPS | Progress: (16/20) | 7.10 s
-[Task 16/25] Current/Best: 10.20/ 22.37 GFLOPS | Progress: (20/20) | 9.11 s Done.
+[Task 16/25] Current/Best: 19.73/ 19.73 GFLOPS | Progress: (4/20) | 3.05 s
+[Task 16/25] Current/Best: 3.00/ 19.73 GFLOPS | Progress: (8/20) | 4.67 s
+[Task 16/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (12/20) | 5.91 s
+[Task 16/25] Current/Best: 17.87/ 19.77 GFLOPS | Progress: (16/20) | 7.26 s
+[Task 16/25] Current/Best: 10.02/ 22.13 GFLOPS | Progress: (20/20) | 9.29 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.29/ 18.31 GFLOPS | Progress: (4/20) | 4.68 s
-[Task 17/25] Current/Best: 14.44/ 23.59 GFLOPS | Progress: (8/20) | 7.53 s
-[Task 17/25] Current/Best: 18.76/ 23.59 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 17/25] Current/Best: 16.65/ 23.59 GFLOPS | Progress: (16/20) | 11.71 s
-[Task 17/25] Current/Best: 10.15/ 23.59 GFLOPS | Progress: (20/20) | 13.81 s Done.
+[Task 17/25] Current/Best: 13.43/ 18.28 GFLOPS | Progress: (4/20) | 4.71 s
+[Task 17/25] Current/Best: 14.41/ 23.26 GFLOPS | Progress: (8/20) | 7.48 s
+[Task 17/25] Current/Best: 17.05/ 23.26 GFLOPS | Progress: (12/20) | 9.54 s
+[Task 17/25] Current/Best: 16.48/ 23.26 GFLOPS | Progress: (16/20) | 11.65 s
+[Task 17/25] Current/Best: 10.06/ 23.26 GFLOPS | Progress: (20/20) | 13.77 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.48/ 17.46 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 18/25] Current/Best: 10.68/ 19.43 GFLOPS | Progress: (8/20) | 7.11 s
-[Task 18/25] Current/Best: 19.56/ 19.56 GFLOPS | Progress: (12/20) | 9.04 s
-[Task 18/25] Current/Best: 10.18/ 19.56 GFLOPS | Progress: (16/20) | 12.58 s
-[Task 18/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (20/20) | 14.08 s Done.
+[Task 18/25] Current/Best: 11.20/ 17.70 GFLOPS | Progress: (4/20) | 3.71 s
+[Task 18/25] Current/Best: 10.54/ 19.93 GFLOPS | Progress: (8/20) | 7.10 s
+[Task 18/25] Current/Best: 19.26/ 19.93 GFLOPS | Progress: (12/20) | 9.03 s
+[Task 18/25] Current/Best: 10.11/ 19.93 GFLOPS | Progress: (16/20) | 12.62 s
+[Task 18/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (20/20) | 14.13 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.27/ 20.56 GFLOPS | Progress: (4/20) | 5.99 s
-[Task 19/25] Current/Best: 2.72/ 20.56 GFLOPS | Progress: (8/20) | 9.20 s
-[Task 19/25] Current/Best: 19.87/ 21.53 GFLOPS | Progress: (12/20) | 11.97 s
-[Task 19/25] Current/Best: 15.23/ 22.21 GFLOPS | Progress: (16/20) | 14.80 s
-[Task 19/25] Current/Best: 2.73/ 23.24 GFLOPS | Progress: (20/20) | 17.60 s Done.
+[Task 19/25] Current/Best: 7.20/ 20.30 GFLOPS | Progress: (4/20) | 5.97 s
+[Task 19/25] Current/Best: 2.69/ 20.30 GFLOPS | Progress: (8/20) | 9.21 s
+[Task 19/25] Current/Best: 19.75/ 21.68 GFLOPS | Progress: (12/20) | 12.02 s
+[Task 19/25] Current/Best: 15.35/ 22.05 GFLOPS | Progress: (16/20) | 14.90 s
+[Task 19/25] Current/Best: 2.70/ 23.25 GFLOPS | Progress: (20/20) | 17.75 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.66/ 15.60 GFLOPS | Progress: (4/20) | 3.34 s Done.
+[Task 20/25] Current/Best: 9.40/ 15.30 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-[Task 20/25] Current/Best: 9.76/ 15.60 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 20/25] Current/Best: 2.35/ 16.95 GFLOPS | Progress: (12/20) | 10.48 s
-[Task 20/25] Current/Best: 11.82/ 16.95 GFLOPS | Progress: (16/20) | 14.15 s
-[Task 20/25] Current/Best: 12.29/ 22.21 GFLOPS | Progress: (20/20) | 16.23 s
+[Task 20/25] Current/Best: 9.63/ 15.30 GFLOPS | Progress: (8/20) | 6.76 s
+[Task 20/25] Current/Best: 2.32/ 16.50 GFLOPS | Progress: (12/20) | 10.68 s
+[Task 20/25] Current/Best: 12.38/ 16.50 GFLOPS | Progress: (16/20) | 14.37 s
+[Task 20/25] Current/Best: 12.44/ 22.13 GFLOPS | Progress: (20/20) | 16.45 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.46/ 17.97 GFLOPS | Progress: (4/20) | 3.22 s
-[Task 21/25] Current/Best: 14.72/ 17.97 GFLOPS | Progress: (8/20) | 4.80 s
-[Task 21/25] Current/Best: 1.63/ 17.97 GFLOPS | Progress: (12/20) | 6.92 s
-[Task 21/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (16/20) | 10.34 s
-[Task 21/25] Current/Best: 4.47/ 18.09 GFLOPS | Progress: (20/20) | 17.40 s
+[Task 21/25] Current/Best: 6.41/ 17.68 GFLOPS | Progress: (4/20) | 3.23 s
+[Task 21/25] Current/Best: 14.65/ 17.68 GFLOPS | Progress: (8/20) | 4.79 s
+[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 6.94 s
+[Task 21/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (16/20) | 10.38 s
+[Task 21/25] Current/Best: 4.45/ 18.14 GFLOPS | Progress: (20/20) | 17.35 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: 9.20/ 21.83 GFLOPS | Progress: (8/20) | 4.68 s
-[Task 22/25] Current/Best: 19.94/ 21.83 GFLOPS | Progress: (12/20) | 7.00 s
-[Task 22/25] Current/Best: 15.45/ 21.83 GFLOPS | Progress: (16/20) | 9.06 s
-[Task 22/25] Current/Best: 14.30/ 21.83 GFLOPS | Progress: (20/20) | 10.71 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.97 GFLOPS | Progress: (4/20) | 2.71 s
+[Task 22/25] Current/Best: 8.71/ 21.83 GFLOPS | Progress: (8/20) | 4.69 s
+[Task 22/25] Current/Best: 20.08/ 21.83 GFLOPS | Progress: (12/20) | 7.01 s
+[Task 22/25] Current/Best: 15.28/ 21.83 GFLOPS | Progress: (16/20) | 9.08 s
+[Task 22/25] Current/Best: 14.45/ 21.83 GFLOPS | Progress: (20/20) | 10.80 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.76/ 21.06 GFLOPS | Progress: (4/20) | 3.22 s
-[Task 23/25] Current/Best: 14.75/ 21.06 GFLOPS | Progress: (8/20) | 6.57 s
-[Task 23/25] Current/Best: 21.01/ 21.60 GFLOPS | Progress: (12/20) | 8.36 s
-[Task 23/25] Current/Best: 6.40/ 21.60 GFLOPS | Progress: (16/20) | 15.24 s
-[Task 23/25] Current/Best: 7.87/ 21.60 GFLOPS | Progress: (20/20) | 19.42 s Done.
+[Task 23/25] Current/Best: 17.63/ 20.60 GFLOPS | Progress: (4/20) | 3.27 s
+[Task 23/25] Current/Best: 13.73/ 20.60 GFLOPS | Progress: (8/20) | 6.65 s
+[Task 23/25] Current/Best: 20.80/ 21.58 GFLOPS | Progress: (12/20) | 8.45 s
+[Task 23/25] Current/Best: 6.24/ 21.58 GFLOPS | Progress: (16/20) | 15.34 s
+[Task 23/25] Current/Best: 7.98/ 21.58 GFLOPS | Progress: (20/20) | 19.51 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.62/ 8.62 GFLOPS | Progress: (4/20) | 11.81 s
-[Task 24/25] Current/Best: 2.11/ 8.62 GFLOPS | Progress: (8/20) | 22.83 s
-[Task 24/25] Current/Best: 4.42/ 8.62 GFLOPS | Progress: (12/20) | 34.37 s Done.
+[Task 24/25] Current/Best: 8.54/ 8.54 GFLOPS | Progress: (4/20) | 11.80 s
+[Task 24/25] Current/Best: 2.14/ 8.54 GFLOPS | Progress: (8/20) | 22.81 s
+[Task 24/25] Current/Best: 4.29/ 8.54 GFLOPS | Progress: (12/20) | 34.35 s Done.
-[Task 24/25] Current/Best: 6.34/ 8.67 GFLOPS | Progress: (16/20) | 39.75 s
-[Task 24/25] Current/Best: 3.29/ 8.67 GFLOPS | Progress: (20/20) | 45.56 s Done.
+[Task 24/25] Current/Best: 5.78/ 8.85 GFLOPS | Progress: (16/20) | 39.64 s
+[Task 24/25] Current/Best: 2.97/ 8.85 GFLOPS | Progress: (20/20) | 45.48 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/ 2.94 GFLOPS | Progress: (4/20) | 11.64 s
-[Task 25/25] Current/Best: 5.58/ 7.91 GFLOPS | Progress: (8/20) | 22.93 s
-[Task 25/25] Current/Best: 5.85/ 7.91 GFLOPS | Progress: (12/20) | 34.45 s
-[Task 25/25] Current/Best: 5.74/ 9.35 GFLOPS | Progress: (16/20) | 36.34 s
-[Task 25/25] Current/Best: 2.91/ 9.35 GFLOPS | Progress: (20/20) | 47.04 s
+[Task 25/25] Current/Best: 1.55/ 2.78 GFLOPS | Progress: (4/20) | 11.61 s
+[Task 25/25] Current/Best: 5.87/ 7.94 GFLOPS | Progress: (8/20) | 22.88 s
+[Task 25/25] Current/Best: 5.95/ 7.94 GFLOPS | Progress: (12/20) | 34.35 s
+[Task 25/25] Current/Best: 5.85/ 9.00 GFLOPS | Progress: (16/20) | 36.09 s
+[Task 25/25] Current/Best: 2.86/ 9.04 GFLOPS | Progress: (20/20) | 46.77 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -981,8 +981,8 @@ 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': 405.6382329199914, 'median': 405.48388540000815, 'std': 0.933472245333622}
-unoptimized: {'mean': 492.48641366999436, 'median': 492.1965809500307, 'std': 0.8522537710826755}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 410.1723779999793, 'median': 410.00709689997166, 'std': 0.6558500357178145}
+unoptimized: {'mean': 491.82149348000166, 'median': 491.77043189997676, 'std': 1.0117483041688307}
</pre></div>
</div>
</div>
@@ -996,7 +996,7 @@ 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 13.849 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 15.354 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 4d1b42582..8fdc28f77 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ 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>1.255e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.305e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 29637e646..2a9ea56d3 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ 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, 0xdc06900)), stage(b, placeholder(b, 0x23622a20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x222d8bc0)), stage(b, placeholder(b, 0x20ffb4b0)), 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=[ [...]
</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 83ec26c64..c318126fe 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>13:01.733</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:09.642</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,50 +336,50 @@
</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>10:13.849</p></td>
+<td><p>10:15.354</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>00:58.483</p></td>
+<tr class="row-even"><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>00:59.913</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>00:53.391</p></td>
+<tr class="row-odd"><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>00:57.582</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>00:30.654</p></td>
+<td><p>00:30.581</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>00:23.999</p></td>
+<td><p>00:24.557</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>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.793</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>00:00.503</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.703</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>00:00.148</p></td>
+<td><p>00:00.152</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>00:00.004</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="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.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="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="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>
-<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="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</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 9a6da600a..c423e7f60 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -594,7 +594,7 @@ compile and run this new schedule with the parallel operation applied:</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallel: 0.000006
+parallel: 0.000007
</pre></div>
</div>
</div>
@@ -668,10 +668,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.460670005661087e-06 1.0
- naive 5.831999999999999e-06 0.6893071111505084
-parallel 5.8522e-06 0.691694628922326
- vector 2.5397399999999995e-05 3.001819002869328
+ numpy 7.78373000684951e-06 1.0
+ naive 5.8138e-06 0.746916965887047
+parallel 6.950399999999999e-06 0.8929395025114952
+ vector 2.4538099999999998e-05 3.1524860161396933
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017634
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017927
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 3.252105
+none: 3.154756
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.295339
+blocking: 0.290210
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.332997
+vectorization: 0.325854
@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], []),
@@ -1215,7 +1215,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.113340
+loop permutation: 0.117447
@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], []),
@@ -1293,7 +1293,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.106468
+array packing: 0.109963
@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], []),
@@ -1369,7 +1369,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.108536
+block caching: 0.111333
@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], []),
@@ -1438,7 +1438,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: 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: 0.144063
+parallelization: 0.144473
@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], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.2521051694 1.0
- blocking 0.2953391412 0.0908147571545138
- vectorization 0.33299698469999994 0.10239428534884575
-loop permutation 0.113339674 0.03485117119410708
- array packing 0.1064680815 0.032738203703185566
- block caching 0.10853594479999999 0.033374057463222945
- parallelization 0.144062898 0.04429835152796704
+ none 3.1547563393 1.0
+ blocking 0.29021008769999995 0.09199128442496254
+ vectorization 0.3258543642 0.10328986747429848
+loop permutation 0.11744688699999999 0.03722851287654753
+ array packing 0.10996334910000001 0.03485636837626562
+ block caching 0.11133254470000001 0.03529037831324345
+ parallelization 0.1444727579 0.04579521914267923
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a