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 2022/12/14 09:18:52 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@c6652bca875f9cc806a88c9e1c740eddec36b030)
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 5e8cdacfdf deploying docs (apache/tvm@c6652bca875f9cc806a88c9e1c740eddec36b030)
5e8cdacfdf is described below
commit 5e8cdacfdf329c77d13fc900b5d690e1b168ef20
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Dec 14 09:18:45 2022 +0000
deploying docs (apache/tvm@c6652bca875f9cc806a88c9e1c740eddec36b030)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 311212 -> 314727 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22989 -> 23008 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.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_adreno.rst.txt | 7 +-
.../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 | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1547 ++++----------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 80 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 87 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../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 | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/genindex.html | 2 +
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 16 +-
docs/how_to/compile_models/from_pytorch.html | 13 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 3 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 47 +-
docs/how_to/deploy_models/deploy_prequantized.html | 12 +-
.../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 | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1547 ++++----------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 80 +-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 87 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../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 | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/objects.inv | Bin 24102 -> 24117 bytes
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/relay/backend.html | 20 +
.../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 | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 272 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
132 files changed, 1550 insertions(+), 3564 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 1d72e25b5c..44d42e7073 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index a545152451..979e8de9bd 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
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 aeaf7bcaf1..7c02fde217 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.614 seconds)
+ **Total running time of the script:** ( 1 minutes 15.543 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index a070702e5e..30629a6d70 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 986ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 1s/step
Keras top-1 id: 285, class name: Egyptian cat
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 73de4da736..68712cff0d 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.zip02c6a30e-9341-42df-9b96-efa68a4c8f18 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1280269e-c883-4cd9-baa7-37e3cc94bc30 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 735b119159..cdbbad39b8 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ 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, 46.0MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 47.8MB/s]
46%|####5 | 18.9M/41.5M [00:00<00:00, 44.5MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 40.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.8MB/s]
88%|########7 | 36.3M/41.5M [00:00<00:00, 44.6MB/s]
98%|#########7| 40.6M/41.5M [00:01<00:00, 33.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 63.0MB/s]
30%|##9 | 12.3M/41.5M [00:00<00:00, 46.2MB/s]
41%|#### | 17.0M/41.5M [00:00<00:00, 39.4MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.4MB/s]
62%|######1 | 25.6M/41.5M [00:00<00:00, 30.8MB/s]
77%|#######7 | 32.1M/41.5M [00:00<00:00, 38.6MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 40.6MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 39.5MB/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 79c6ec5355..fc556e4ea1 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
14%|#4 | 6.30M/44.7M [00:00<00:00, 47.7MB/s]
32%|###2 | 14.3M/44.7M [00:00<00:00, 40.6MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 52.9MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 55.0MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 61.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 54.9MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 63.0MB/s]
32%|###2 | 14.4M/44.7M [00:00<00:00, 64.9MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 73.5MB/s]
69%|######9 | 31.0M/44.7M [00:00<00:00, 69.2MB/s]
84%|########4 | 37.6M/44.7M [00:00<00:00, 68.5MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 66.3MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 67.9MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index b9b0e80ea7..c79f4825f3 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.723 seconds)
+ **Total running time of the script:** ( 1 minutes 18.184 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 bbe0b69053..17dbb3bca8 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:53.913** total execution time for **how_to_compile_models** files:
+**06:09.422** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.723 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:18.184 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:12.614 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:15.543 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:48.130 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:51.272 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.139 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:34.135 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.266 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.264 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.071 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:28.407 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.754 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.038 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.247 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.055 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.467 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.007 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.502 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.516 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index d2a40c6dc5..3cedd2d32c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,13 +723,18 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2520.1820 2519.4955 2522.6710 2518.6284 1.3762
+ 3344.7055 3344.2562 3351.2438 3342.4476 2.4506
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.529 seconds)
+
+
.. _sphx_glr_download_how_to_deploy_models_deploy_model_on_adreno.py:
.. only:: html
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 a0a4f29b54..8cbb29ed5e 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
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 17.1123 17.2048 17.3267 16.3535 0.2654
+ 17.2004 17.4280 17.7261 16.5236 0.4765
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 e6e52c3cc8..252c97f4af 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
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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%|4 | 7.99M/170M [00:00<00:02, 61.3MB/s]
8%|8 | 14.3M/170M [00:00<00:02, 56.8MB/s]
12%|#1 | 19.7M/170M [00:00<00:03, 52.2MB/s]
15%|#5 | 26.0M/170M [00:00<00:02, 57.0MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 51.3MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 60.1MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 54.8MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 52.8MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 54.9MB/s]
44%|####3 | 74.1M/170M [00:01<00:01, 67.0MB/s]
48%|####7 | 81.0M/170M [00:01<00:01, 67.1MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 58.2MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 56.3MB/s]
61%|######1 | 104M/170M [00:01<00:01, 61.4MB/s]
65%|######4 | 110M/170M [00:01<00:01, 62.1MB/s]
69%|######8 | 117M/170M [00:02<00:00, 64.2MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 64.4MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 63.6MB/s]
83%|########2 | 140M/170M [00:02<00:00, 57.7MB/s]
86%|########5 | 146M/170M [00:02<00:00, 49.6MB/s]
89%|########9 | 152M/170M [00:02<00:00, 47.8MB/s]
93%|#########3| 158M/170M [00:02<00:00, 48.9MB/s]
96%|#########6| 163M/170M [00:03<00:00, 44.0MB/s]
99%|#########8| 168M/170M [00:03<00:00, 39.6MB/s]
100%|##########| 170M/170M [00:03<00:00, 54.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
8%|8 | 14.3M/170M [00:00<00:01, 113MB/s]
15%|#4 | 25.1M/170M [00:00<00:01, 76.2MB/s]
19%|#9 | 32.8M/170M [00:00<00:02, 65.5MB/s]
25%|##4 | 42.1M/170M [00:00<00:01, 74.3MB/s]
29%|##9 | 49.6M/170M [00:00<00:02, 58.9MB/s]
36%|###5 | 60.6M/170M [00:00<00:01, 72.7MB/s]
40%|#### | 68.4M/170M [00:01<00:01, 64.2MB/s]
46%|####6 | 78.3M/170M [00:01<00:01, 61.7MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 65.8MB/s]
56%|#####5 | 94.3M/170M [00:01<00:01, 61.5MB/s]
59%|#####9 | 101M/170M [00:01<00:01, 49.0MB/s]
62%|######2 | 106M/170M [00:01<00:01, 42.9MB/s]
70%|######9 | 119M/170M [00:01<00:00, 61.6MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 68.7MB/s]
80%|######## | 136M/170M [00:02<00:00, 62.1MB/s]
85%|########4 | 144M/170M [00:02<00:00, 66.2MB/s]
89%|########9 | 152M/170M [00:02<00:00, 66.6MB/s]
95%|#########5| 161M/170M [00:02<00:00, 74.4MB/s]
99%|#########9| 169M/170M [00:02<00:00, 63.3MB/s]
100%|##########| 170M/170M [00:02<00:00, 64.1MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 23.871 seconds)
+ **Total running time of the script:** ( 3 minutes 35.974 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 ab37c62b2a..fdcb554838 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
47%|####6 | 6.30M/13.6M [00:00<00:00, 31.9MB/s]
69%|######8 | 9.34M/13.6M [00:00<00:00, 28.8MB/s]
90%|########9 | 12.2M/13.6M [00:00<00:00, 24.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 28.6MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
47%|####6 | 6.30M/13.6M [00:00<00:00, 38.8MB/s]
74%|#######3 | 10.0M/13.6M [00:00<00:00, 37.1MB/s]
100%|#########9| 13.5M/13.6M [00:00<00:00, 35.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 36.4MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.6430 90.5211 94.4103 90.0929 0.6280
+ 90.6887 90.6066 92.3708 90.2499 0.3538
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.265 seconds)
+ **Total running time of the script:** ( 1 minutes 10.756 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 c4bcc19eb3..81b8d6f4c2 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
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.9839 119.8273 123.2217 118.6827 0.7435
+ 121.5437 121.5220 127.4966 120.0875 0.9109
@@ -469,7 +469,7 @@ 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:** ( 2 minutes 25.273 seconds)
+ **Total running time of the script:** ( 2 minutes 32.589 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 c0d30ba87f..b9a35b7da5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 42.158 seconds)
+ **Total running time of the script:** ( 1 minutes 44.935 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 5869bb7745..65ad0ba514 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
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7228/132723 [00:00<00:01, 72268.87KB/s]
12%|#2 | 15952/132723 [00:00<00:01, 81072.29KB/s]
19%|#8 | 24708/132723 [00:00<00:01, 84031.76KB/s]
25%|##5 | 33479/132723 [00:00<00:01, 85479.90KB/s]
32%|###1 | 42258/132723 [00:00<00:01, 86310.17KB/s]
38%|###8 | 51029/132723 [00:00<00:00, 86782.32KB/s]
45%|####5 | 59738/132723 [00:00<00:00, 86881.37KB/s]
52%|#####1 | 68527/132723 [00:00<00:00, 87199.50KB/s]
58%|#####8 | 77286/132723 [00:00<00:00, 87318.40KB/s]
65%|######4 | 86018/132723 [00:01<00:00, 75419.08KB/s]
71%|#######1 | 94689/132723 [00:01<00:00, 78529.65KB/s]
78%|#######7 | 103341/132723 [00:01<00:00, 80784.43KB/s]
84%|########4 | 112061/132723 [00:01<00:00, 82626.45KB/s]
91%|######### | 120716/132723 [00:01<00:00, 83766.04KB/s]
97%|#########7| 129317/132723 [00:01<00:00, 84422.61KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 83338.25KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 4765/132723 [00:00<00:02, 47640.16KB/s]
9%|9 | 12284/132723 [00:00<00:01, 63841.38KB/s]
15%|#5 | 20245/132723 [00:00<00:01, 71037.92KB/s]
21%|##1 | 28039/132723 [00:00<00:01, 73759.28KB/s]
27%|##7 | 35937/132723 [00:00<00:01, 75639.91KB/s]
33%|###3 | 43866/132723 [00:00<00:01, 76878.27KB/s]
39%|###8 | 51591/132723 [00:00<00:01, 76997.89KB/s]
45%|####4 | 59291/132723 [00:00<00:00, 76505.44KB/s]
50%|##### | 66943/132723 [00:00<00:00, 75997.90KB/s]
56%|#####6 | 74544/132723 [00:01<00:00, 75859.19KB/s]
62%|######1 | 82131/132723 [00:01<00:00, 75563.67KB/s]
68%|######7 | 89688/132723 [00:01<00:00, 75250.46KB/s]
73%|#######3 | 97214/132723 [00:01<00:00, 75018.69KB/s]
79%|#######8 | 104717/132723 [00:01<00:00, 74703.44KB/s]
85%|########4 | 112188/132723 [00:01<00:00, 73632.65KB/s]
90%|#########
| 119555/132723 [00:01<00:00, 73446.02KB/s]
96%|#########5| 126912/132723 [00:01<00:00, 73479.56KB/s]
100%|##########| 132723/132723 [00:01<00:00, 73779.67KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 10.982 seconds)
+ **Total running time of the script:** ( 3 minutes 19.080 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 24a1e85b99..21b1c57319 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
@@ -5,26 +5,26 @@
Computation times
=================
-**14:09.445** total execution time for **how_to_deploy_models** files:
+**14:58.233** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:23.871 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:35.974 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:10.982 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:19.080 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:25.273 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:32.589 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.158 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:44.935 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.265 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.756 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:51.722 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:02.529 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.634 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:38.496 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.559 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.048 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.973 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.820 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 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 212aa93860..9067ef5119 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
@@ -472,7 +472,7 @@ 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.zip0c9ce879-6ac9-4da0-a888-956a05311c3f from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipe58f0129-2794-4194-8ac9-91ff29a821b4 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 2048911a9f..40d54f7d36 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
=================
-**00:48.625** total execution time for **how_to_extend_tvm** files:
+**00:50.865** 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``) | 00:45.094 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:47.138 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.467 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.613 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.104 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.009 | 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 998889cb7d..cf41181989 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: 7371us [7371us] (46.76%; 46.76%)
- FoldScaleAxis: 8394us [9us] (53.24%; 53.24%)
- FoldConstant: 8385us [1696us] (53.19%; 99.90%)
- InferType: 6689us [6689us] (42.43%; 79.77%)
+ InferType: 7798us [7798us] (46.60%; 46.60%)
+ FoldScaleAxis: 8937us [10us] (53.40%; 53.40%)
+ FoldConstant: 8927us [1854us] (53.34%; 99.89%)
+ InferType: 7072us [7072us] (42.26%; 79.23%)
@@ -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: 6753us [6753us] (44.93%; 44.93%)
- FoldScaleAxis: 8276us [5us] (55.07%; 55.07%)
- FoldConstant: 8271us [1690us] (55.03%; 99.94%)
- InferType: 6581us [6581us] (43.79%; 79.56%)
+ InferType: 7066us [7066us] (44.29%; 44.29%)
+ FoldScaleAxis: 8887us [8us] (55.71%; 55.71%)
+ FoldConstant: 8879us [1759us] (55.66%; 99.91%)
+ InferType: 7119us [7119us] (44.63%; 80.18%)
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 d747e7e6a8..6547a40845 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: 43.208671 ms
+ Convolution: 41.493152 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 cd68e61825..131e13bdbc 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
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.363766 ms
+ conv2d with tensor core: 11.915680 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 f4aa4ad5a5..9c2b38760a 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: 0.019119
- Baseline: 3.291093
+ Numpy running time: 0.019706
+ Baseline: 3.558644
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.313798
+ Opt1: 0.339654
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.348404
+ Opt2: 0.359926
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117668
+ Opt3: 0.143151
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109544
+ Opt4: 0.110794
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.112521
+ Opt5: 0.113632
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147766
+ Opt6: 0.150467
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 871507d03d..6b8a849e59 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
=================
-**00:34.989** total execution time for **how_to_optimize_operators** files:
+**00:36.852** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.416 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:34.225 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.521 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.543 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.051 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.085 | 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 b52629c1dc..63eac47ce9 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
=================
-**09:12.158** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:30.178** 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``) | 05:42.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:53.358 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.260 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:36.872 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.661 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.523 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.806 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.452 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.342 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.779 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.457 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.194 | 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 d5005feced..6f8c3103d3 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -239,679 +239,159 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[15] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
- let cse_var_1: int32 = (rc.outer.outer*196)
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 30), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*16)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*16), 81)) && (floormod((threadIdx.x_1*16), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 81)*49)) + (floordiv(floormod((threadIdx.x_1*16), 81), 9)*7)) + floormod((threadIdx.x_1*7), 9)) [...]
+ pad_temp.shared_1[((threadIdx.x_1*16) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 1), 81)) && (floormod(((threadIdx.x_1*16) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 2), 81)) && (floormod(((threadIdx.x_1*16) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 3), 81)) && (floormod(((threadIdx.x_1*16) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 4)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 4), 81)) && (floormod(((threadIdx.x_1*16) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 5)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 6)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 7)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 8)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 10)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 11)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 12)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 13)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 14)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 15)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[(threadIdx.x_2*16)] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod((threadIdx.x_2*16), 36), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 784)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 55), 81)) && (floormod(((threadIdx.x_1*16) + 55), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 55), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 1)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 785)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 56), 81)) && (floormod(((threadIdx.x_1*16) + 56), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 56), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 2)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 786)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 57), 81)) && (floormod(((threadIdx.x_1*16) + 57), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 57), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 3)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 787)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 58), 81)) && (floormod(((threadIdx.x_1*16) + 58), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 58), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 4)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 788)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 59), 81)) && (floormod(((threadIdx.x_1*16) + 59), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 59), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 5)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 789)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 60), 81)) && (floormod(((threadIdx.x_1*16) + 60), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 60), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 6)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 790)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 61), 81)) && (floormod(((threadIdx.x_1*16) + 61), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 61), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 7)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 791)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 62), 81)) && (floormod(((threadIdx.x_1*16) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 62), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 8)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 792)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)) && (floormod(((threadIdx.x_1*16) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 9)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 793)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 64), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 10)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 794)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 65), 81)) && (floormod(((threadIdx.x_1*16) + 65), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 65), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 11)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 795)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 66), 81)) && (floormod(((threadIdx.x_1*16) + 66), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 66), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 12)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 796)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 67), 81)) && (floormod(((threadIdx.x_1*16) + 67), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 67), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 13)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 797)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 68), 81)) && (floormod(((threadIdx.x_1*16) + 68), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 68), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 14)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 798)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 69), 81)) && (floormod(((threadIdx.x_1*16) + 69), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 69), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 15)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 799)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 70), 81)) && (floormod(((threadIdx.x_1*16) + 70), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 70), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 98), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 98), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 147)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 147), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 1)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 196), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 245)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 245), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 101), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 294), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 343)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 343), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 441)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 441), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 490), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 58), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 37), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 539)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 539), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 107), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.inner: int32, 0, 16) {
+ let cse_var_3: int32 = (rc.inner*9)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_3]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 288)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 432)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 289)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 145)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 433)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 290)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 146)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 434)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 291)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 147)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 435)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 292)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 148)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 436)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 293)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 149)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 437)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 294)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 150)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 438)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 295)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 151)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 439)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 296)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 152)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 440)]))
}
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[144]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[288]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[432]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[3]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[147]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[291]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[435]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[6]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[150]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[294]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[438]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[36]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[180]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[324]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[468]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[39]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[183]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[327]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[471]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[42]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[186]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[330]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[474]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[72]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[216]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[360]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[504]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[75]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[219]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[363]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[507]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[78]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[222]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[366]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[510]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[108]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[252]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[396]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[540]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[111]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[255]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[399]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[543]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[114]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[258]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[402]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[546]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[145]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[289]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[433]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[4]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[148]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[292]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[436]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[7]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[151]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[295]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[439]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[37]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[181]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[325]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[469]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[40]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[184]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[328]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[472]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[43]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[187]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[331]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[475]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[73]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[217]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[361]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[505]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[76]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[220]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[364]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[508]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[79]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[223]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[367]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[511]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[109]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[253]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[397]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[541]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[112]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[256]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[400]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[544]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[115]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[259]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[403]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[547]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[146]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[290]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[434]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[5]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[149]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[293]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[437]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[8]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[152]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[296]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[440]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[38]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[182]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[326]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[470]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[41]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[185]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[329]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[473]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[44]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[188]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[332]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[476]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[74]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[218]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[362]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[506]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[77]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[221]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[365]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[509]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[80]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[224]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[368]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[512]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[110]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[254]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[398]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[542]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[113]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[257]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[401]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[545]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[116]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[260]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[404]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[548]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[9]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[153]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[297]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[441]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[12]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[156]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[300]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[444]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[15]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[159]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[303]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[447]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[45]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[189]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[333]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[477]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[48]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[192]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[336]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[480]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[51]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[195]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[339]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[483]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[81]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[225]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[369]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[513]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[84]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[228]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[372]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[516]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[87]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[231]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[375]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[519]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[117]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[261]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[405]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[549]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[120]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[264]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[408]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[552]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[123]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[267]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[411]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[555]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[10]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[154]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[298]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[442]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[13]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[157]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[301]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[445]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[16]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[160]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[304]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[448]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[46]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[190]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[334]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[478]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[49]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[193]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[337]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[481]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[52]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[196]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[340]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[484]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[82]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[226]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[370]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[514]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[85]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[229]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[373]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[517]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[88]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[232]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[376]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[520]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[118]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[262]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[406]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[550]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[121]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[265]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[409]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[553]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[124]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[268]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[412]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[556]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[11]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[155]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[299]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[443]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[14]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[158]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[302]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[446]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[17]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[161]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[305]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[449]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[47]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[191]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[335]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[479]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[50]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[194]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[338]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[482]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[53]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[197]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[341]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[485]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[83]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[227]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[371]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[515]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[86]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[230]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[374]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[518]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[89]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[233]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[377]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[521]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[119]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[263]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[407]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[551]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[122]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[266]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[410]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[554]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[125]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[269]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[413]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[557]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[18]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[162]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[306]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[450]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[21]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[165]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[309]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[453]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[24]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[168]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[312]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[456]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[54]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[198]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[342]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[486]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[57]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[201]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[345]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[489]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[60]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[204]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[348]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[492]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[90]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[234]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[378]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[522]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[93]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[237]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[381]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[525]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[96]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[240]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[384]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[528]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[126]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[270]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[414]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[558]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[129]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[273]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[417]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[561]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[132]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[276]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[420]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[564]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[19]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[163]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[307]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[451]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[22]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[166]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[310]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[454]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[25]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[169]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[313]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[457]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[55]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[199]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[343]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[487]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[58]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[202]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[346]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[490]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[61]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[205]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[349]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[493]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[91]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[235]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[379]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[523]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[94]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[238]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[382]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[526]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[97]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[241]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[385]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[529]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[127]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[271]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[415]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[559]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[130]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[274]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[418]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[562]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[133]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[277]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[421]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[565]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[20]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[164]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[308]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[452]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[23]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[167]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[311]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[455]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[26]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[170]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[314]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[458]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[56]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[200]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[344]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[488]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[59]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[203]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[347]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[491]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[62]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[206]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[350]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[494]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[92]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[236]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[380]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[524]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[95]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[239]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[383]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[527]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[98]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[242]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[386]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[530]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[128]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[272]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[416]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[560]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[131]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[275]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[419]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[563]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[134]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[278]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[422]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[566]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[27]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[171]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[315]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[459]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[30]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[174]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[318]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[462]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[33]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[177]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[321]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[465]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[63]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[207]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[351]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[495]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[66]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[210]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[354]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[498]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[69]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[213]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[357]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[501]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[99]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[243]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[387]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[531]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[102]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[246]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[390]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[534]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[105]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[249]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[393]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[537]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[135]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[279]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[423]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[567]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[138]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[282]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[426]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[570]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[141]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[285]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[429]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[573]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[28]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[172]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[316]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[460]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[31]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[175]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[319]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[463]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[34]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[178]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[322]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[466]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[64]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[208]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[352]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[496]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[67]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[211]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[355]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[499]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[70]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[214]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[358]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[502]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[100]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[244]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[388]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[532]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[103]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[247]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[391]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[535]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[106]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[250]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[394]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[538]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[136]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[280]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[424]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[568]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[139]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[283]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[427]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[571]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[142]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[286]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[430]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[574]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[29]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[173]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[317]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[461]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[32]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[176]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[320]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[464]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[35]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[179]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[323]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[467]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[65]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[209]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[353]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[497]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[68]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[212]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[356]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[500]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[71]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[215]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[359]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[503]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[101]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[245]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[389]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[533]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[104]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[248]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[392]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[536]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[107]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[251]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[395]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[539]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[137]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[281]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[425]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[569]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[140]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[284]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[428]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[572]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[143]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[287]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[431]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[575]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*16) + i1.inner)]), 0f32)
- compute_3[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[(((blockIdx.x*16) + i1.inner) + 4)]), 0f32)
- compute_3[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 392)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias_3[(((blockIdx.x*16) + i1.inner) + 8)]), 0f32)
- compute_3[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 588)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias_3[(((blockIdx.x*16) + i1.inner) + 12)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*4) + i1.inner)]), 0f32)
+ compute_3[((((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias_3[(((blockIdx.x*4) + i1.inner) + 2)]), 0f32)
}
}
}
@@ -966,7 +446,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.288 ms
+ Execution time of this operator: 0.326 ms
@@ -1014,10 +494,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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)
@@ -1026,19 +506,19 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+ 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)
@@ -1061,16 +541,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=16)
+ 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=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ 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=16)
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=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1089,667 +569,136 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define uint64_t unsigned long long
#endif
extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[324];
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[1296];
__shared__ float kernel_shared[576];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 30) {
- pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((((int)threadIdx.x) < 21) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 294) / 81) * 49)) + (((((int)threadIdx.x) + 51) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((9 <= ((((int)threadIdx.x) * 16) % 81)) && (((((int)threadIdx.x) * 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 16) / 81) * 49)) + ((((((int)threadIdx.x) * 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((9 <= (((((int)threadIdx.x) * 16) + 1) % 81)) && ((((((int)threadIdx.x) * 16) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((9 <= (((((int)threadIdx.x) * 16) + 2) % 81)) && ((((((int)threadIdx.x) * 16) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((9 <= (((((int)threadIdx.x) * 16) + 3) % 81)) && ((((((int)threadIdx.x) * 16) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((9 <= (((((int)threadIdx.x) * 16) + 4) % 81)) && ((((((int)threadIdx.x) * 16) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 4) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 5) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 6) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 7) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 8) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 9) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 10) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 11) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 12) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 13) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 14) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 15) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 784)] = (((((9 <= (((((int)threadIdx.x) * 16) + 55) % 81)) && ((((((int)threadIdx.x) * 16) + 55) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 784) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 55) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[(((int)threadIdx.x) * 16)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) * 16) % 36) / 3) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 785)] = (((((9 <= (((((int)threadIdx.x) * 16) + 56) % 81)) && ((((((int)threadIdx.x) * 16) + 56) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 785) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 56) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 1) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 786)] = (((((9 <= (((((int)threadIdx.x) * 16) + 57) % 81)) && ((((((int)threadIdx.x) * 16) + 57) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 786) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 57) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 2) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 787)] = (((((9 <= (((((int)threadIdx.x) * 16) + 58) % 81)) && ((((((int)threadIdx.x) * 16) + 58) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 787) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 58) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 788)] = (((((9 <= (((((int)threadIdx.x) * 16) + 59) % 81)) && ((((((int)threadIdx.x) * 16) + 59) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 788) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 59) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 789)] = (((((9 <= (((((int)threadIdx.x) * 16) + 60) % 81)) && ((((((int)threadIdx.x) * 16) + 60) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 789) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 60) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 5) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 790)] = (((((9 <= (((((int)threadIdx.x) * 16) + 61) % 81)) && ((((((int)threadIdx.x) * 16) + 61) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 790) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 61) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 791)] = (((((9 <= (((((int)threadIdx.x) * 16) + 62) % 81)) && ((((((int)threadIdx.x) * 16) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 791) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 7) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 792)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 16) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 792) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 793)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 64) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 793) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 794)] = (((((9 <= (((((int)threadIdx.x) * 16) + 65) % 81)) && ((((((int)threadIdx.x) * 16) + 65) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 794) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 65) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 10) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 795)] = (((((9 <= (((((int)threadIdx.x) * 16) + 66) % 81)) && ((((((int)threadIdx.x) * 16) + 66) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 795) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 66) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 11) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 796)] = (((((9 <= (((((int)threadIdx.x) * 16) + 67) % 81)) && ((((((int)threadIdx.x) * 16) + 67) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 796) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 67) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 797)] = (((((9 <= (((((int)threadIdx.x) * 16) + 68) % 81)) && ((((((int)threadIdx.x) * 16) + 68) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 797) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 68) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 13) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 798)] = (((((9 <= (((((int)threadIdx.x) * 16) + 69) % 81)) && ((((((int)threadIdx.x) * 16) + 69) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 798) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 69) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 14) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 799)] = (((((9 <= (((((int)threadIdx.x) * 16) + 70) % 81)) && ((((((int)threadIdx.x) * 16) + 70) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 799) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 70) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 18432) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 49) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 98) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 147) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 52) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 101) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 343) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 55) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 441) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 58) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 37) {
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 539) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 107) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[144]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[288]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[432]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[3]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[147]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[291]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[435]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[6]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[150]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[294]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[438]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[36]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[180]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[324]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[468]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[39]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[183]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[327]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[471]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[42]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[186]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[330]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[474]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[72]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[216]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[360]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[504]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[75]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[219]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[363]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[507]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[78]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[222]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[366]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[510]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[108]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[252]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[396]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[540]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[111]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[255]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[399]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[543]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[114]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[258]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[402]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[546]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[145]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[289]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[433]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[4]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[148]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[292]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[436]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[7]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[151]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[295]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[439]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[37]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[181]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[325]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[469]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[40]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[184]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[328]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[472]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[43]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[187]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[331]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[475]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[73]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[217]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[361]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[505]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[76]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[220]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[364]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[508]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[79]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[223]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[367]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[511]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[109]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[253]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[397]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[541]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[112]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[256]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[400]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[544]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[115]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[259]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[403]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[547]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[146]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[290]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[434]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[5]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[149]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[293]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[437]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[8]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[152]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[296]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[440]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[38]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[182]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[326]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[470]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[41]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[185]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[329]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[473]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[44]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[188]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[332]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[476]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[74]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[218]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[362]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[506]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[77]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[221]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[365]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[509]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[80]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[224]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[368]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[512]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[110]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[254]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[398]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[542]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[113]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[257]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[401]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[545]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[116]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[260]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[404]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[548]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[9]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[153]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[297]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[441]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[12]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[156]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[300]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[444]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[15]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[159]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[303]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[447]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[45]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[189]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[333]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[477]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[48]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[192]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[336]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[480]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[51]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[195]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[339]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[483]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[81]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[225]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[369]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[513]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[84]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[228]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[372]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[516]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[87]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[231]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[375]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[519]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[117]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[261]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[405]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[549]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[120]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[264]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[408]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[552]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[123]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[267]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[411]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[555]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[10]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[154]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[298]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[442]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[13]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[157]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[301]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[445]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[16]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[160]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[304]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[448]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[46]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[190]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[334]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[478]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[49]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[193]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[337]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[481]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[52]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[196]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[340]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[484]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[82]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[226]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[370]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[514]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[85]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[229]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[373]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[517]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[88]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[232]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[376]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[520]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[118]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[262]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[406]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[550]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[121]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[265]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[409]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[553]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[124]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[268]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[412]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[556]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[11]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[155]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[299]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[443]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[14]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[158]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[302]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[446]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[17]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[161]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[305]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[449]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[47]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[191]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[335]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[479]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[50]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[194]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[338]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[482]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[53]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[197]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[341]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[485]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[83]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[227]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[371]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[515]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[86]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[230]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[374]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[518]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[89]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[233]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[377]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[521]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[119]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[263]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[407]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[551]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[122]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[266]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[410]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[554]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[125]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[269]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[413]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[557]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[18]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[162]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[306]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[450]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[21]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[165]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[309]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[453]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[24]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[168]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[312]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[456]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[54]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[198]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[342]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[486]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[57]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[201]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[345]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[489]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[60]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[204]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[348]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[492]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[90]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[234]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[378]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[522]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[93]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[237]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[381]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[525]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[96]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[240]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[384]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[528]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[126]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[270]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[414]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[558]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[129]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[273]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[417]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[561]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[132]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[276]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[420]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[564]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[19]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[163]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[307]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[451]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[22]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[166]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[310]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[454]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[25]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[169]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[313]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[457]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[55]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[199]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[343]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[487]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[58]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[202]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[346]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[490]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[61]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[205]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[349]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[493]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[91]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[235]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[379]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[523]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[94]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[238]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[382]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[526]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[97]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[241]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[385]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[529]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[127]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[271]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[415]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[559]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[130]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[274]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[418]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[562]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[133]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[277]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[421]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[565]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[20]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[164]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[308]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[452]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[23]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[167]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[311]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[455]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[26]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[170]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[314]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[458]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[56]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[200]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[344]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[488]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[59]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[203]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[347]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[491]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[62]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[206]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[350]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[494]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[92]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[236]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[380]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[524]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[95]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[239]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[383]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[527]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[98]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[242]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[386]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[530]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[128]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[272]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[416]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[560]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[131]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[275]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[419]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[563]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[134]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[278]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[422]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[566]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[27]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[171]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[315]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[459]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[30]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[174]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[318]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[462]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[33]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[177]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[321]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[465]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[63]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[207]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[351]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[495]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[66]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[210]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[354]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[498]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[69]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[213]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[357]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[501]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[99]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[243]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[387]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[531]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[102]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[246]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[390]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[534]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[105]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[249]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[393]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[537]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[135]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[279]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[423]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[567]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[138]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[282]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[426]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[570]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[141]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[285]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[429]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[573]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[28]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[172]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[316]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[460]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[31]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[175]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[319]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[463]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[34]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[178]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[322]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[466]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[64]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[208]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[352]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[496]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[67]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[211]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[355]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[499]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[70]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[214]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[358]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[502]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[100]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[244]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[388]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[532]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[103]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[247]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[391]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[535]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[106]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[250]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[394]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[538]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[136]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[280]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[424]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[568]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[139]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[283]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[427]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[571]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[142]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[286]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[430]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[574]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[29]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[173]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[317]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[461]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[32]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[176]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[320]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[464]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[35]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[179]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[323]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[467]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[65]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[209]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[353]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[497]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[68]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[212]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[356]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[500]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[71]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[215]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[359]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[503]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[101]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[245]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[389]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[533]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[104]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[248]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[392]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[536]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[107]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[251]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[395]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[539]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[137]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[281]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[425]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[569]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[140]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[284]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[428]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[572]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[143]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[287]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[431]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[575]));
+ for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_inner * 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 288)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 432)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 289)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 433)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 290)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 434)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 291)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 435)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 292)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 436)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 293)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 437)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 294)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 438)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 295)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 439)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 296)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 440)]));
+ }
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
}
}
@@ -1811,7 +760,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 42.632 seconds)
+ **Total running time of the script:** ( 5 minutes 53.358 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 c226ba3a7f..309b1ed035 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
@@ -643,7 +643,7 @@ 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)
- 7.8963 7.8910 7.9117 7.8861 0.0111
+ 7.8843 7.8850 7.8855 7.8822 0.0014
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.661 seconds)
+ **Total running time of the script:** ( 1 minutes 4.523 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
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 02d4d14d56..f559245613 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
@@ -662,7 +662,7 @@ 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)
- 769.0901 768.2937 770.8430 768.1336 1.2412
+ 798.6117 796.5761 804.8121 794.4470 4.4696
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.260 seconds)
+ **Total running time of the script:** ( 1 minutes 36.872 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 97f3347400..f91ff0db53 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
@@ -386,27 +386,77 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
for (i.outer.inner: int32, 0, 16) {
for (nb_j.inner: int32, 0, 2) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ }
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = (((i.outer.inner*32) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_4]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -462,7 +512,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.215 ms
+ Execution time of this operator: 1.877 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 5dd6a176fd..63596800b1 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:41.200** total execution time for **how_to_tune_with_autotvm** files:
+**00:32.925** 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``) | 00:41.164 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:32.886 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.023 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index aeda8dc347..516681bdae 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
@@ -387,7 +387,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4335673
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1250330
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -510,8 +510,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6639821
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2243359
+ No: 3 GFLOPS: 137.13/137.13 result: MeasureResult(costs=(0.001688228484375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8228330612182617, timestamp=1671007996.2653587) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2035242
+ No: 4 GFLOPS: 0.00/137.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -633,9 +634,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3120208
- No: 4 GFLOPS: 2.03/2.03 result: MeasureResult(costs=(0.11384416950000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.947231769561768, timestamp=1670956837.3610103) [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4960400
- No: 5 GFLOPS: 0.00/2.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5935863
+ No: 5 GFLOPS: 0.00/137.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -757,8 +757,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 512, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8305009
- No: 6 GFLOPS: 0.00/2.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8861027
+ No: 6 GFLOPS: 293.95/293.95 result: MeasureResult(costs=(0.0007875517784810127,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.497633218765259, timestamp=1671007999.9878116) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10076014
+ No: 7 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -880,9 +881,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6949955
- No: 7 GFLOPS: 328.23/328.23 result: MeasureResult(costs=(0.000705303540229885,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4255976676940918, timestamp=1670956839.9784958) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10104172
- No: 8 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,472548
+ No: 8 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1004,8 +1004,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5369278
- No: 9 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7273113
+ No: 9 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1127,8 +1127,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4831392
- No: 10 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7718880
+ No: 10 GFLOPS: 20.44/293.95 result: MeasureResult(costs=(0.011325489444444444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2964777946472168, timestamp=1671008002.5026994) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6589441
+ No: 11 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1250,9 +1251,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5582594
- No: 11 GFLOPS: 8.22/328.23 result: MeasureResult(costs=(0.0281544475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.20864200592041, timestamp=1670956843.4195638) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3717727
- No: 12 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5577743
+ No: 12 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1374,8 +1374,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5394013
- No: 13 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4405992
+ No: 13 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1497,8 +1497,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1445666
- No: 14 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8740001
+ No: 14 GFLOPS: 31.31/293.95 result: MeasureResult(costs=(0.007393682142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2788639068603516, timestamp=1671008005.121807) [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5879075
+ No: 15 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1620,9 +1621,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3342585
- No: 15 GFLOPS: 437.31/437.31 result: MeasureResult(costs=(0.0005293790394736843,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8600027561187744, timestamp=1670956845.514734) [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8809357
- No: 16 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2598122
+ No: 16 GFLOPS: 2.46/293.95 result: MeasureResult(costs=(0.0942582855,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.017066717147827, timestamp=1671008006.7710116) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2209904
+ No: 17 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1744,8 +1745,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,503824
- No: 17 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10162174
+ No: 18 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1867,8 +1868,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5360249
- No: 18 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5912159
+ No: 19 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1990,26 +1991,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6752374
- No: 19 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,455347
- No: 20 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1275280
+ No: 20 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2131,7 +2114,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8474203
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8954779
@@ -2186,9 +2169,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8809357
+ [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10076014
Finish loading 20 records
- Time cost of this operator: 0.000876
+ Time cost of this operator: 0.000993
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 ca80032b50..53c03501f9 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 312.0 98.723 (1, 2, 10, 10, 3) 2 1 [312.0]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.048 0.965 (1, 6, 10, 10) 1 1 [3.048]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.987 0.312 (1, 1, 10, 10, 3) 1 1 [0.987]
- Total_time - 316.035 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.706 (1, 2, 10, 10, 3) 2 1 [309.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.057 0.975 (1, 6, 10, 10) 1 1 [3.057]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.001 0.319 (1, 1, 10, 10, 3) 1 1 [1.001]
+ Total_time - 313.658 - - - - -
@@ -397,10 +397,10 @@ 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 135.5 97.813 (1, 6, 10, 10, 1) 2 1 [135.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.053 1.482 (1, 6, 10, 10) 1 1 [2.053]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.705 (1, 1, 10, 10, 3) 1 1 [0.976]
- Total_time - 138.53 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 108.1 97.532 (1, 6, 10, 10, 1) 2 1 [108.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 1.594 (1, 6, 10, 10) 1 1 [1.767]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.874 (1, 1, 10, 10, 3) 1 1 [0.969]
+ Total_time - 110.835 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 5ceceadf2d..1cffd60b7e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 42.3MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 44.5MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.313 seconds)
+ **Total running time of the script:** ( 1 minutes 7.774 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
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 ab35f41e4e..9b4370ea8f 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/tmp_90n_aec/images/random'
+ '/tmp/tmp31ymcrcs/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp_90n_aec/images/target contains 8144 images
- /tmp/tmp_90n_aec/images/random contains 5000 images
+ /tmp/tmp31ymcrcs/images/target contains 8144 images
+ /tmp/tmp31ymcrcs/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2193 - accuracy: 0.9270 - val_loss: 0.1186 - val_accuracy: 0.9554 - 47s/epoch - 145ms/step
+ 328/328 - 48s - loss: 0.2307 - accuracy: 0.9188 - val_loss: 0.1351 - val_accuracy: 0.9573 - 48s/epoch - 146ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.1000 - accuracy: 0.9647 - val_loss: 0.1079 - val_accuracy: 0.9592 - 44s/epoch - 133ms/step
+ 328/328 - 45s - loss: 0.0960 - accuracy: 0.9642 - val_loss: 0.1324 - val_accuracy: 0.9611 - 45s/epoch - 136ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0669 - accuracy: 0.9759 - val_loss: 0.1258 - val_accuracy: 0.9551 - 43s/epoch - 133ms/step
+ 328/328 - 44s - loss: 0.0706 - accuracy: 0.9745 - val_loss: 0.1178 - val_accuracy: 0.9588 - 44s/epoch - 134ms/step
- <keras.callbacks.History object at 0x7fa19d8c21d0>
+ <keras.callbacks.History object at 0x7f98dfaec790>
@@ -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:** ( 4 minutes 43.584 seconds)
+ **Total running time of the script:** ( 4 minutes 56.774 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 d391447931..77ec82a4b1 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
@@ -5,18 +5,18 @@
Computation times
=================
-**06:53.951** total execution time for **how_to_work_with_microtvm** files:
+**07:12.258** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:43.584 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:56.774 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:05.313 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:07.774 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:53.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:55.358 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.087 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.260 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.960 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.090 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 529f07d82c..2836aef14e 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
=================
-**00:44.835** total execution time for **how_to_work_with_relay** files:
+**00:47.134** 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``) | 00:32.987 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:34.968 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.262 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.520 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.579 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.639 | 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 9dde8ff2eb..16d365397f 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 0x7fa19e08d050>
+ <function my_cuda_math_rule at 0x7f98e0e81f80>
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 59259dc133..6c5860732f 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:08.488** total execution time for **how_to_work_with_schedules** files:
+**00:08.368** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.990 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.703 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.237 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.593 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.609 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.589 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.121 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.051 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.053 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.031 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.025 | 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 b2199ae615..53c1142c56 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpyi_arhl_/input0.cc'\nsource_filename = \"/tmp/tmpyi_arhl_/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/tmp04e4wlo9/input0.cc'\nsource_filename = \"/tmp/tmp04e4wlo9/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 b8990ff897..9dd63b8331 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
=================
-**00:27.120** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:28.131** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.114 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:28.125 | 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 959980dcaa..1a217bc4b4 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ 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 30.05s!
+ resnet18_v1 inference graph built in 31.31s!
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 451a76b64e..9e09a406e4 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 20.10s!
+ yolov3-tiny inference graph built in 20.99s!
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 6632fa81cc..23e277f8f1 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
=================
-**01:42.170** total execution time for **topic_vta_tutorials_frontend** files:
+**01:44.890** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.136 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:53.455 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.034 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.435 | 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 27fae9ec1c..97fc823a65 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
=================
-**00:03.220** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.235** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.747 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.753 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.473 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.482 | 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 6e6c759cb1..d9c4c160c1 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
=================
-**00:00.841** total execution time for **topic_vta_tutorials** files:
+**00:00.848** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.447 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.450 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.395 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.399 | 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 8c860ddad4..740c3a33b2 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
-
- *E
-
@@ -332,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 98.020 ms
+ Execution time of this operator: 95.845 ms
@@ -450,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 28.480 seconds)
+ **Total running time of the script:** ( 1 minutes 26.399 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index e55973fd6f..cab0b34fc1 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 2.19/2.19 result: MeasureResult(costs=(0.12236583720000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2158772945404053, timestamp=1670955369.5738146) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
- No: 2 GFLOPS: 1.61/2.19 result: MeasureResult(costs=(0.16625437599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8978428840637207, timestamp=1670955372.4807696) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
- No: 3 GFLOPS: 1.91/2.19 result: MeasureResult(costs=(0.14053541139999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.485870838165283, timestamp=1670955375.7764509) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 4 GFLOPS: 1.71/2.19 result: MeasureResult(costs=(0.1571701744,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7366943359375, timestamp=1670955379.314839) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
- No: 5 GFLOPS: 11.16/11.16 result: MeasureResult(costs=(0.0240434364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6191384792327881, timestamp=1670955380.8985522) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
- No: 6 GFLOPS: 12.18/12.18 result: MeasureResult(costs=(0.0220395392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.579561710357666, timestamp=1670955381.5079334) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 7 GFLOPS: 11.62/12.18 result: MeasureResult(costs=(0.0230923776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6502034664154053, timestamp=1670955382.137204) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
- No: 8 GFLOPS: 12.54/12.54 result: MeasureResult(costs=(0.021403288200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5823304653167725, timestamp=1670955382.7391253) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
- No: 9 GFLOPS: 2.03/12.54 result: MeasureResult(costs=(0.13206080979999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3163766860961914, timestamp=1670955385.1772897) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
- No: 10 GFLOPS: 3.27/12.54 result: MeasureResult(costs=(0.0821763226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5262548923492432, timestamp=1670955386.7436786) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
+ No: 1 GFLOPS: 3.40/3.40 result: MeasureResult(costs=(0.0788423086,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5135166645050049, timestamp=1671006457.2592132) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
+ No: 2 GFLOPS: 7.07/7.07 result: MeasureResult(costs=(0.037969686600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8380458354949951, timestamp=1671006458.122872) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+ No: 3 GFLOPS: 12.84/12.84 result: MeasureResult(costs=(0.0209029732,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6002449989318848, timestamp=1671006459.540642) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+ No: 4 GFLOPS: 0.51/12.84 result: MeasureResult(costs=(0.5294922854,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.716930866241455, timestamp=1671006469.1044455) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+ No: 5 GFLOPS: 1.72/12.84 result: MeasureResult(costs=(0.15631917339999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.726470708847046, timestamp=1671006472.8233833) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+ No: 6 GFLOPS: 12.50/12.84 result: MeasureResult(costs=(0.021474067,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6199052333831787, timestamp=1671006473.429413) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+ No: 7 GFLOPS: 10.40/12.84 result: MeasureResult(costs=(0.025814160600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.64272141456604, timestamp=1671006474.1021602) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 8 GFLOPS: 12.73/12.84 result: MeasureResult(costs=(0.0210851084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6033406257629395, timestamp=1671006474.7040255) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
+ No: 9 GFLOPS: 3.51/12.84 result: MeasureResult(costs=(0.07658358579999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4424622058868408, timestamp=1671006476.261223) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 10 GFLOPS: 1.61/12.84 result: MeasureResult(costs=(0.1668642154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.883350133895874, timestamp=1671006479.1867938) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index d73c2274c9..808fbf6689 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 520.0242369199975, 'median': 520.119645799997, 'std': 2.3306879659144153}
+ {'mean': 525.7948484799978, 'median': 525.4736514499939, 'std': 2.3593836329757543}
@@ -554,31 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 13.49/ 17.57 GFLOPS | Progress: (4/20) | 11.37 s
[Task 1/25] Current/Best: 7.64/ 18.57 GFLOPS | Progress: (8/20) | 15.12 s
[Task 1/25] Current/Best: 15.32/ 18.57 GFLOPS | Progress: (12/20) | 19.88 s
[Task 1/25] Current/Best: 22.58/ 22.58 GFLOPS | Progress: (16/20) | 22.63 s
[Task 1/25] Current/Best: 12.33/ 22.58 GFLOPS | Progress: (20/20) | 26.40 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.19/ 16.82 GFLOPS | Progress: (4/20) | 4.02 s
[Task 2/25] Current/Best: 17.45/ 18.94 GFLOPS | Progress: (8/20) | 5.51 s
[Task 2/25] Current/Best: 16.81/ 18.94 GFLOPS | Progress: (12/20) | 7.65 s
[Task 2/25] Current/Best: 21.47/ 21.47 GFLOPS | Progress: (16/20) | 9.22 s
[Task 2/25] Current/Best: 11.14/ 21.47 GFLOPS | Progress: (20/20) | 10.72 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 17.73/ 17.73 GFLOPS | Progress: (4/20) | 5.27 s
[Task 3/25] Current/Best: 10.05/ 17.73 GFLOPS | Progress: (8/20) | 7.45 s
[Task 3/25] Current/Best: 17.40/ 20.28 GFLOPS | Progress: (12/20) | 9.76 s
[Task 3/25] Current/Best: 18.33/ 20.28 GFLOPS | Progress: (16/20) | 12.62 s
[Task 3/25] Current/Best: 14.59/ 20.28 GFLOPS | Progress: (20/20) | 15.06 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.28/ 15.64 GFLOPS | Progress: (4/20) | 6.24 s
[Task 4/25] Current/Best: 10.70/ 15.64 GFLOPS | Progress: (8/20) | 10.87 s
[Task 4/25] Current/Best: 15.17/ 16.37 GFLOPS | Progress: (12/20) | 13.18 s
[Task 4/25] Current/Best: 14.45/ 16.37 GFLOPS | Progress: (16/20) | 15.34 s
[Task 4/25] Current/Best: 11.91/ 17.71 GFLOPS | Progress: (20/20) | 18.19 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 10.50/ 15.96 GFLOPS | Progress: (4/20) | 5.11 s
[Task 5/25] Current/Best: 9.53/ 20.37 GFLOPS | Progress: (8/20) | 7.23 s
[Task 5/25] Current/Best: 11.51/ 20.37 GFLOPS | Progress: (12/20) | 10.24 s
[Task 5/25] Current/Best: 2.64/ 20.37 GFLOPS | Progress: (16/20) | 12.44 s
[Task 5/25] Current/Best: 2.73/ 20.37 GFLOPS | Progress: (20/20) | 14.52 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.67/ 19.76 GFLOPS | Progress: (4/20) | 3.99 s
[Task 6/25] Current/Best: 21.39/ 21.39 GFLOPS | Progress: (8/20) | 6.54 s
[Task 6/25] Current/Best: 8.91/ 21.39 GFLOPS | Progress: (12/20) | 9.18 s
[Task 6/25] Current/Best: 9.13/ 21.39 GFLOPS | Progress: (16/20) | 11.45 s
[Task 6/25] Current/Best: 9.67/ 21.39 GFLOPS | Progress: (20/20) | 18.40 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 7.70/ 17.99 GFLOPS | Progress: (4/20) | 4.48 s
[Task 7/25] Current/Best: 9.56/ 17.99 GFLOPS | Progress: (8/20) | 7.60 s
[Task 7/25] Current/Best: 14.28/ 17.99 GFLOPS | Progress: (12/20) | 10.21 s
[Task 7/25] Current/Best: 6.37/ 19.99 GFLOPS | Progress: (16/20) | 14.31 s
[Task 7/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (20/20) | 16.62 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.58/ 12.62 GFLOPS | Progress: (4/20) | 9.06 s
[Task 8/25] Current/Best: 2.62/ 14.15 GFLOPS | Progress: (8/20) | 21.18 s
[Task 8/25] Current/Best: 15.38/ 15.72 GFLOPS | Progress: (12/20) | 23.47 s
[Task 8/25] Current/Best: 4.50/ 15.72 GFLOPS | Progress: (16/20) | 25.99 s
[Task 8/25] Current/Best: 11.79/ 15.72 GFLOPS | Progress: (20/20) | 29.97 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 12.23/ 12.23 GFLOPS | Progress: (4/20) | 12.64 s
[Task 9/25] Current/Best: 8.30/ 13.79 GFLOPS | Progress: (8/20) | 15.55 s
[Task 9/25] Current/Best: 7.32/ 15.61 GFLOPS | Progress: (12/20) | 17.88 s
[Task 9/25] Current/Best: 16.09/ 21.61 GFLOPS | Progress: (16/20) | 19.35 s
[Task 9/25] Current/Best: 20.88/ 21.61 GFLOPS | Progress: (20/20) | 21.44 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 12.80/ 15.97 GFLOPS | Progress: (4/20) | 3.89 s
[Task 10/25] Current/Best: 10.03/ 15.97 GFLOPS | Progress: (8/20) | 6.42 s
[Task 10/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (12/20) | 8.35 s
[Task 10/25] Current/Best: 9.55/ 16.95 GFLOPS | Progress: (16/20) | 10.68 s
[Task 10/25] Current/Best: 13.63/ 16.95 GFLOPS | Progress: (20/2
0) | 12.84 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 16.25/ 20.16 GFLOPS | Progress: (4/20) | 5.85 s
[Task 11/25] Current/Best: 4.56/ 20.16 GFLOPS | Progress: (8/20) | 8.36 s
[Task 11/25] Current/Best: 13.05/ 20.16 GFLOPS | Progress: (12/20) | 11.28 s
[Task 11/25] Current/Best: 15.88/ 20.16 GFLOPS | Progress: (16/20) | 14.29 s
[Task 11/25] Current/Best: 15.02/ 20.16 GFLOPS | Progress: (20/20) | 16.92 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 3.62/ 18.71 GFLOPS | Progress: (4/20) | 4.26 s
[Task 12/25] Current/Best: 13.29/ 20.64 GFLOPS | Progress: (8/20) | 7.14 s
[Task 12/25] Current/Best: 15.62/ 20.64 GFLOPS | Progress: (12/20) | 9.00 s
[Task 12/25] Current/Best: 3.01/ 20.64 GFLOPS | Progress: (16/20) | 11.87 s
[Task 12/25] Current/Best: 12.39/ 20.64 GFLOPS | Progress: (20/20) | 15.54 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 23.30/ 23.30 GFLOPS | Progress: (4/20) | 5.05 s
[Task 13/25] Current/Best: 11.47/ 23.30 GFLOPS | Progress: (8/20) | 10.55 s
[Task 13/25] Current/Best: 19.85/ 23.30 GFLOPS | Progress: (12/20) | 14.41 s
[Task 13/25] Current/Best: 19.13/ 23.30 GFLOPS | Progress: (16/20) | 17.53 s
[Task 13/25] Current/Best: 8.70/ 23.30 GFLOPS | Progress: (20/20) | 20.36 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 10.99/ 16.30 GFLOPS | Progress: (4/20) | 5.02 s
[Task 14/25] Current/Best: 21.25/ 21.25 GFLOPS | Progress: (8/20) | 7.57 s
[Task 14/25] Current/Best: 18.62/ 21.25 GFLOPS | Progress: (12/20) | 10.58 s
[Task 14/25] Current/Best: 10.11/ 21.25 GFLOPS | Progress: (16/20) | 14.50 s
[Task 14/25] Current/Best: 9.45/ 21.25 GFLOPS | Progress: (20/20) | 18.67 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.58/ 19.13 GFLOPS | Progress: (4/20) | 3.81 s
[Task 15/25] Current/Best: 12.03/ 19.13 GFLOPS | Progress: (8/20) | 7.54 s
[Task 15/25] Current/Best: 16.21/ 22.37 GFLOPS | Progress: (12/20) | 12.00 s
[Task 15/25] Current/Best: 15.19/ 22.37 GFLOPS | Progress: (16/20) | 14.16 s
[Task 15/25] Current/Best: 17.28/ 22.37 GFLOPS | Progress: (20/20) | 16.52 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 11.08/ 19.66 GFLOPS | Progress: (4/20) | 4.96 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.47/ 16.77 GFLOPS | Progress: (4/20) | 8.20 s
[Task 1/25] Current/Best: 8.31/ 18.25 GFLOPS | Progress: (8/20) | 12.11 s
[Task 1/25] Current/Best: 7.37/ 18.25 GFLOPS | Progress: (12/20) | 14.50 s
[Task 1/25] Current/Best: 8.96/ 18.74 GFLOPS | Progress: (16/20) | 18.37 s
[Task 1/25] Current/Best: 12.81/ 18.74 GFLOPS | Progress: (20/20) | 21.71 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 15.45/ 15.45 GFLOPS | Progress: (4/20) | 4.26 s
[Task 2/25] Current/Best: 12.95/ 18.13 GFLOPS | Progress: (8/20) | 5.86 s
[Task 2/25] Current/Best: 13.46/ 18.13 GFLOPS | Progress: (12/20) | 7.68 s
[Task 2/25] Current/Best: 3.73/ 18.13 GFLOPS | Progress: (16/20) | 10.92 s
[Task 2/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (20/20) | 12.69 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 9.69/ 19.91 GFLOPS | Progress: (4/20) | 4.66 s
[Task 3/25] Current/Best: 14.55/ 19.91 GFLOPS | Progress: (8/20) | 7.48 s
[Task 3/25] Current/Best: 16.54/ 19.91 GFLOPS | Progress: (12/20) | 10.64 s
[Task 3/25] Current/Best: 10.66/ 19.91 GFLOPS | Progress: (16/20) | 14.69 s
[Task 3/25] Current/Best: 10.39/ 19.91 GFLOPS | Progress: (20/20) | 17.51 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 8.66/ 12.68 GFLOPS | Progress: (4/20) | 4.03 s
[Task 4/25] Current/Best: 14.41/ 17.10 GFLOPS | Progress: (8/20) | 5.97 s
[Task 4/25] Current/Best: 16.82/ 17.10 GFLOPS | Progress: (12/20) | 12.08 s
[Task 4/25] Current/Best: 9.34/ 17.10 GFLOPS | Progress: (16/20) | 15.05 s
[Task 4/25] Current/Best: 13.97/ 17.10 GFLOPS | Progress: (20/20) | 19.70 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 10.60/ 14.72 GFLOPS | Progress: (4/20) | 4.26 s
[Task 5/25] Current/Best: 12.88/ 15.73 GFLOPS | Progress: (8/20) | 6.67 s
[Task 5/25] Current/Best: 11.66/ 15.73 GFLOPS | Progress: (12/20) | 8.62 s
[Task 5/25] Current/Best: 18.12/ 18.35 GFLOPS | Progress: (16/20) | 11.18 s
[Task 5/25] Current/Best: 5.77/ 18.35 GFLOPS | Progress: (20/20) | 13.15 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.15/ 13.44 GFLOPS | Progress: (4/20) | 5.65 s
[Task 6/25] Current/Best: 4.02/ 18.32 GFLOPS | Progress: (8/20) | 9.51 s
[Task 6/25] Current/Best: 11.98/ 18.32 GFLOPS | Progress: (12/20) | 12.13 s
[Task 6/25] Current/Best: 19.67/ 19.67 GFLOPS | Progress: (16/20) | 16.43 s
[Task 6/25] Current/Best: 14.35/ 19.67 GFLOPS | Progress: (20/20) | 19.71 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 7.68/ 21.00 GFLOPS | Progress: (4/20) | 5.24 s
[Task 7/25] Current/Best: 3.09/ 21.00 GFLOPS | Progress: (8/20) | 9.59 s
[Task 7/25] Current/Best: 3.12/ 21.00 GFLOPS | Progress: (12/20) | 12.62 s
[Task 7/25] Current/Best: 15.80/ 21.00 GFLOPS | Progress: (16/20) | 15.66 s
[Task 7/25] Current/Best: 15.51/ 21.00 GFLOPS | Progress: (20/20) | 17.93 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.59/ 12.59 GFLOPS | Progress: (4/20) | 10.86 s
[Task 8/25] Current/Best: 15.86/ 15.86 GFLOPS | Progress: (8/20) | 20.37 s
[Task 8/25] Current/Best: 2.88/ 15.86 GFLOPS | Progress: (12/20) | 30.72 s
[Task 8/25] Current/Best: 12.10/ 15.86 GFLOPS | Progress: (16/20) | 34.03 s
[Task 8/25] Current/Best: 2.78/ 17.46 GFLOPS | Progress: (20/20) | 40.51 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.33/ 13.33 GFLOPS | Progress: (4/20) | 13.01 s
[Task 9/25] Current/Best: 6.63/ 13.33 GFLOPS | Progress: (8/20) | 17.54 s
[Task 9/25] Current/Best: 5.18/ 15.56 GFLOPS | Progress: (12/20) | 23.36 s
[Task 9/25] Current/Best: 5.86/ 20.36 GFLOPS | Progress: (16/20) | 24.95 s
[Task 9/25] Current/Best: 10.54/ 20.36 GFLOPS | Progress: (20/20) | 28.67 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 3.02/ 19.69 GFLOPS | Progress: (4/20) | 3.87 s
[Task 10/25] Current/Best: 13.05/ 19.69 GFLOPS | Progress: (8/20) | 5.74 s
[Task 10/25] Current/Best: 5.63/ 19.69 GFLOPS | Progress: (12/20) | 7.65 s
[Task 10/25] Current/Best: 4.83/ 19.69 GFLOPS | Progress: (16/20) | 10.68 s
[Task 10/25] Current/Best: 12.87/ 19.69 GFLOPS | Progress: (20/2
0) | 12.42 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 17.25/ 19.30 GFLOPS | Progress: (4/20) | 4.92 s
[Task 11/25] Current/Best: 7.98/ 19.30 GFLOPS | Progress: (8/20) | 7.42 s
[Task 11/25] Current/Best: 17.44/ 19.30 GFLOPS | Progress: (12/20) | 10.60 s
[Task 11/25] Current/Best: 23.48/ 23.48 GFLOPS | Progress: (16/20) | 13.16 s
[Task 11/25] Current/Best: 12.63/ 23.48 GFLOPS | Progress: (20/20) | 15.94 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.44/ 18.33 GFLOPS | Progress: (4/20) | 4.45 s
[Task 12/25] Current/Best: 17.75/ 18.33 GFLOPS | Progress: (8/20) | 11.16 s
[Task 12/25] Current/Best: 4.26/ 18.33 GFLOPS | Progress: (12/20) | 13.93 s
[Task 12/25] Current/Best: 16.20/ 18.33 GFLOPS | Progress: (16/20) | 16.42 s
[Task 12/25] Current/Best: 5.68/ 18.33 GFLOPS | Progress: (20/20) | 20.04 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 17.17/ 18.26 GFLOPS | Progress: (4/20) | 4.33 s
[Task 13/25] Current/Best: 18.12/ 18.26 GFLOPS | Progress: (8/20) | 9.18 s
[Task 13/25] Current/Best: 17.73/ 18.26 GFLOPS | Progress: (12/20) | 11.36 s
[Task 13/25] Current/Best: 11.56/ 18.26 GFLOPS | Progress: (16/20) | 14.87 s
[Task 13/25] Current/Best: 13.46/ 19.35 GFLOPS | Progress: (20/20) | 17.48 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.02/ 20.25 GFLOPS | Progress: (4/20) | 5.71 s
[Task 14/25] Current/Best: 8.71/ 20.25 GFLOPS | Progress: (8/20) | 10.35 s
[Task 14/25] Current/Best: 9.85/ 20.25 GFLOPS | Progress: (12/20) | 16.73 s
[Task 14/25] Current/Best: 13.24/ 20.25 GFLOPS | Progress: (16/20) | 19.40 s
[Task 14/25] Current/Best: 12.53/ 20.25 GFLOPS | Progress: (20/20) | 22.54 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.94/ 15.94 GFLOPS | Progress: (4/20) | 4.77 s
[Task 15/25] Current/Best: 3.09/ 15.94 GFLOPS | Progress: (8/20) | 8.80 s
[Task 15/25] Current/Best: 1.70/ 17.04 GFLOPS | Progress: (12/20) | 11.97 s Done.
+
[Task 15/25] Current/Best: 6.87/ 17.04 GFLOPS | Progress: (16/20) | 14.16 s
[Task 15/25] Current/Best: 15.75/ 17.04 GFLOPS | Progress: (20/20) | 15.91 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.07/ 14.63 GFLOPS | Progress: (4/20) | 4.15 s
[Task 16/25] Current/Best: 7.95/ 17.62 GFLOPS | Progress: (8/20) | 5.83 s
[Task 16/25] Current/Best: 9.87/ 17.62 GFLOPS | Progress: (12/20) | 8.23 s
[Task 16/25] Current/Best: 7.03/ 17.62 GFLOPS | Progress: (16/20) | 13.06 s
[Task 16/25] Current/Best: 11.96/ 17.62 GFLOPS | Progress: (20/20) | 15.23 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 16.38/ 20.28 GFLOPS | Progress: (4/20) | 6.29 s
[Task 17/25] Current/Best: 16.17/ 20.28 GFLOPS | Progress: (8/20) | 8.48 s
[Task 17/25] Current/Best: 7.75/ 21.02 GFLOPS | Progress: (12/20) | 10.88 s
[Task 17/25] Current/Best: 20.39/ 21.02 GFLOPS | Progress: (16/20) | 13.25 s
[Task 17/25] Current/Best: 10.71/ 21.02 GFLOPS | Progress: (20/20) | 15.99 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 3.10/ 16.55 GFLOPS | Progress: (4/20) | 4.63 s
[Task 18/25] Current/Best: 17.36/ 17.36 GFLOPS | Progress: (8/20) | 8.34 s
[Task 18/25] Current/Best: 15.08/ 17.36 GFLOPS | Progress: (12/20) | 11.66 s
[Task 18/25] Current/Best: 10.04/ 21.82 GFLOPS | Progress: (16/20) | 17.43 s
[Task 18/25] Current/Best: 16.39/ 21.82 GFLOPS | Progress: (20/20) | 19.66 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.48/ 19.41 GFLOPS | Progress: (4/20) | 4.26 s
[Task 19/25] Current/Best: 21.11/ 23.07 GFLOPS | Progress: (8/20) | 7.79 s
[Task 19/25] Current/Best: 11.35/ 23.07 GFLOPS | Progress: (12/20) | 12.03 s
[Task 19/25] Current/Best: 18.36/ 23.07 GFLOPS | Progress: (16/20) | 14.37 s
[Task 19/25] Current/Best: 19.54/ 23.07 GFLOPS | Progress: (20/20) | 18.97 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.85/ 17.46 GFLOPS | Progress: (4/20) | 3.98 s
[Task 20/25] Current/Best: 10.58/ 17.46 GFLOPS | Progress: (8/20) | 6.65 s
[Task 20/25] Current/Best: 13.64/ 17.46 GFLOPS | Progress: (12/20) | 10.02 s
[Task 20/25] Current/Best: 4.61/ 17.46 GFLOPS | Progress: (16/20) | 13.17 s
[Task 20/25] Current/Best: 19.33/ 19.33 GFLOPS | Progress: (20/20) | 15.43 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 11.82/ 11.82 GFLOPS | Progress: (4/20) | 5.58 s
[Task 21/25] Current/Best: 2.46/ 15.13 GFLOPS | Progress: (8/20) | 7.64 s
[Task 21/25] Current/Best: 16.02/ 16.02 GFLOPS | Progress: (12/20) | 10.01 s
[Task 21/25] Current/Best: 15.99/ 18.44 GFLOPS | Progress: (16/20) | 12.43 s
[Task 21/25] Current/Best: 3.12/ 18.44 GFLOPS | Progress: (20/20
) | 15.14 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 16/25] Current/Best: 8.00/ 19.66 GFLOPS | Progress: (8/20) | 6.82 s
[Task 16/25] Current/Best: 11.55/ 19.66 GFLOPS | Progress: (12/20) | 9.18 s
[Task 16/25] Current/Best: 11.42/ 19.66 GFLOPS | Progress: (16/20) | 12.48 s
[Task 16/25] Current/Best: 5.98/ 19.66 GFLOPS | Progress: (20/20) | 15.66 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 8.82/ 16.54 GFLOPS | Progress: (4/20) | 4.12 s
[Task 17/25] Current/Best: 22.02/ 22.02 GFLOPS | Progress: (8/20) | 6.19 s
[Task 17/25] Current/Best: 5.34/ 22.02 GFLOPS | Progress: (12/20) | 8.85 s
[Task 17/25] Current/Best: 9.40/ 22.02 GFLOPS | Progress: (16/20) | 12.56 s
[Task 17/25] Current/Best: 22.98/ 22.98 GFLOPS | Progress: (20/20) | 15.80 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 17.04/ 21.16 GFLOPS | Progress: (4/20) | 3.53 s
[Task 18/25] Current/Best: 5.87/ 23.43 GFLOPS | Progress: (8/20) | 5.90 s
[Task 18/25] Current/Best: 18.79/ 23.43 GFLOPS | Progress: (12/20) | 7.70 s
[Task 18/25] Current/Best: 19.55/ 23.43 GFLOPS | Progress: (16/20) | 10.52 s
[Task 18/25] Current/Best: 9.04/ 23.43 GFLOPS | Progress: (20/20) | 16.13 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (4/20) | 5.46 s
[Task 19/25] Current/Best: 12.20/ 19.72 GFLOPS | Progress: (8/20) | 10.79 s
[Task 19/25] Current/Best: 17.24/ 19.72 GFLOPS | Progress: (12/20) | 13.69 s
[Task 19/25] Current/Best: 8.27/ 19.72 GFLOPS | Progress: (16/20) | 17.92 s
[Task 19/25] Current/Best: 12.15/ 19.90 GFLOPS | Progress: (20/20) | 21.84 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 2.29/ 12.71 GFLOPS | Progress: (4/20) | 6.15 s
[Task 20/25] Current/Best: 10.47/ 12.71 GFLOPS | Progress: (8/20) | 8.17 s
[Task 20/25] Current/Best: 8.12/ 14.29 GFLOPS | Progress: (12/20) | 11.75 s
[Task 20/25] Current/Best: 8.61/ 14.29 GFLOPS | Progress: (16/20) | 15.12 s
[Task 20/25] Current/Best: 14.66/ 17.44 GFLOPS | Progress: (20/20) | 17.01 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 10.32/ 18.75 GFLOPS | Progress: (4/20) | 4.74 s
[Task 21/25] Current/Best: 4.33/ 18.75 GFLOPS | Progress: (8/20) | 6.37 s
[Task 21/25] Current/Best: 6.48/ 21.20 GFLOPS | Progress: (12/20) | 8.84 s
[Task 21/25] Current/Best: 19.36/ 21.20 GFLOPS | Progress: (16/20) | 11.02 s
[Task 21/25] Current/Best: 13.71/ 21.20 GFLOPS | Progress: (20/20)
| 12.94 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.90/ 15.90 GFLOPS | Progress: (4/20) | 6.93 s
[Task 22/25] Current/Best: 9.61/ 15.90 GFLOPS | Progress: (8/20) | 8.77 s
[Task 22/25] Current/Best: 10.92/ 17.68 GFLOPS | Progress: (12/20) | 10.42 s
[Task 22/25] Current/Best: 8.08/ 19.69 GFLOPS | Progress: (16/20) | 12.32 s
[Task 22/25] Current/Best: 8.14/ 19.69 GFLOPS | Progress: (20/20) | 15.17 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 9.96/ 11.95 GFLOPS | Progress: (4/20) | 6.79 s
[Task 23/25] Current/Best: 11.94/ 17.85 GFLOPS | Progress: (8/20) | 10.36 s
[Task 23/25] Current/Best: 14.30/ 18.59 GFLOPS | Progress: (12/20) | 13.34 s
[Task 23/25] Current/Best: 13.68/ 18.59 GFLOPS | Progress: (16/20) | 17.42 s
[Task 23/25] Current/Best: 18.16/ 18.59 GFLOPS | Progress: (20/20) | 20.61 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.03/ 4.03 GFLOPS | Progress: (4/20) | 12.84 s Done.
- Done.
-
[Task 24/25] Current/Best: 5.64/ 6.33 GFLOPS | Progress: (8/20) | 19.04 s
[Task 24/25] Current/Best: 8.85/ 8.85 GFLOPS | Progress: (12/20) | 23.52 s
[Task 24/25] Current/Best: 6.96/ 8.85 GFLOPS | Progress: (16/20) | 33.88 s
[Task 24/25] Current/Best: 1.44/ 8.85 GFLOPS | Progress: (20/20) | 44.95 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 9.06/ 9.06 GFLOPS | Progress: (4/20) | 6.87 s
[Task 25/25] Current/Best: 5.75/ 9.06 GFLOPS | Progress: (8/20) | 17.80 s
[Task 25/25] Current/Best: 3.96/ 9.06 GFLOPS | Progress: (12/20) | 29.64 s Done.
-
[Task 25/25] Current/Best: 2.89/ 9.06 GFLOPS | Progress: (16/20) | 41.42 s
[Task 25/25] Current/Best: 5.16/ 9.06 GFLOPS | Progress: (20/20) | 43.55 s
+
[Task 22/25] Current/Best: 16.67/ 17.80 GFLOPS | Progress: (4/20) | 4.48 s
[Task 22/25] Current/Best: 4.62/ 17.80 GFLOPS | Progress: (8/20) | 6.46 s
[Task 22/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (12/20) | 8.50 s
[Task 22/25] Current/Best: 14.44/ 18.50 GFLOPS | Progress: (16/20) | 11.43 s
[Task 22/25] Current/Best: 8.56/ 18.50 GFLOPS | Progress: (20/20) | 13.84 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 13.96/ 23.07 GFLOPS | Progress: (4/20) | 4.68 s
[Task 23/25] Current/Best: 13.83/ 23.07 GFLOPS | Progress: (8/20) | 6.99 s
[Task 23/25] Current/Best: 9.12/ 23.07 GFLOPS | Progress: (12/20) | 9.64 s
[Task 23/25] Current/Best: 11.79/ 23.07 GFLOPS | Progress: (16/20) | 12.59 s
[Task 23/25] Current/Best: 20.54/ 23.07 GFLOPS | Progress: (20/20) | 18.35 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.66/ 7.66 GFLOPS | Progress: (4/20) | 12.61 s
[Task 24/25] Current/Best: 2.44/ 7.66 GFLOPS | Progress: (8/20) | 23.61 s
[Task 24/25] Current/Best: 5.49/ 7.66 GFLOPS | Progress: (12/20) | 35.18 s
[Task 24/25] Current/Best: 7.96/ 7.96 GFLOPS | Progress: (16/20) | 40.12 s
[Task 24/25] Current/Best: 2.79/ 9.59 GFLOPS | Progress: (20/20) | 48.29 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 3.52/ 8.17 GFLOPS | Progress: (4/20) | 4.58 s
[Task 25/25] Current/Best: 2.99/ 8.17 GFLOPS | Progress: (8/20) | 6.00 s
[Task 25/25] Current/Best: 3.31/ 8.17 GFLOPS | Progress: (12/20) | 8.63 s
[Task 25/25] Current/Best: 1.52/ 8.17 GFLOPS | Progress: (16/20) | 10.32 s
[Task 25/25] Current/Best: 7.94/ 8.17 GFLOPS | Progress: (20/20) | 21.28 s
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 425.32732617999727, 'median': 425.49077234999686, 'std': 2.3648607733454887}
- unoptimized: {'mean': 520.0242369199975, 'median': 520.119645799997, 'std': 2.3306879659144153}
+ optimized: {'mean': 443.2241799900021, 'median': 442.8553297999997, 'std': 1.2358620085024732}
+ unoptimized: {'mean': 525.7948484799978, 'median': 525.4736514499939, 'std': 2.3593836329757543}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 48.924 seconds)
+ **Total running time of the script:** ( 11 minutes 59.482 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 c27e5ef78a..bc19b003d9 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 2.054e-07 secs/op
+ 1.285e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 8244797f39..5868bee525 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x21b372b0)), stage(b, placeholder(b, 0x1a82a290)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0xd9615d0)), stage(b, placeholder(b, 0xeb9fdd0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 6e3906ecb2..5b1d54b916 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
=================
-**15:17.700** total execution time for **tutorial** files:
+**15:34.667** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:48.924 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:59.482 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:28.480 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:26.399 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.927 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.489 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.164 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.672 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.655 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:28.023 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.535 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.555 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.833 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.844 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.171 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.191 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 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 |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 979036eb84..688ce6ad69 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
- naive: 0.000007
+ Numpy running time: 0.000008
+ naive: 0.000008
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000008
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.184270000379911e-06 1.0
- naive 6.6858000000000004e-06 0.930616471770472
- parallel 6.9414999999999995e-06 0.96620811851906
- vector 2.4681399999999997e-05 3.4354777867055137
+ numpy 7.699140001022897e-06 1.0
+ naive 7.8285e-06 1.0168018764381368
+ parallel 7.745299999999999e-06 1.0059954746856101
+ vector 2.45903e-05 3.193902175662862
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018643
+ Numpy running time: 0.019289
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.304013
+ none: 3.442906
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.305587
+ blocking: 0.330149
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.348980
+ vectorization: 0.352015
@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, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.119618
+ loop permutation: 0.143185
@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, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109821
+ array packing: 0.109962
@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, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110859
+ block caching: 0.113218
@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, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.149532
+ parallelization: 0.148249
@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, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3040130473 1.0
- blocking 0.3055870649 0.09248966651318828
- vectorization 0.3489801616 0.10562311849379119
- loop permutation 0.11961816480000001 0.03620390206925803
- array packing 0.10982061369999999 0.03323855327682319
- block caching 0.1108594217 0.03355296123621334
- parallelization 0.1495322029 0.04525775193962867
+ none 3.4429063483 1.0
+ blocking 0.3301487045 0.0958924440866703
+ vectorization 0.3520149301 0.10224353917550329
+ loop permutation 0.1431853593 0.04158851412577646
+ array packing 0.10996156940000001 0.03193858858644111
+ block caching 0.11321799670000002 0.0328844253216192
+ parallelization 0.1482489117 0.04305923446718227
@@ -1652,6 +1652,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.489 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index c3324f01a4..9c9146fd6d 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-c547bbb13d2c42b7c447dfaee74734e2f7ffe18c
+c6652bca875f9cc806a88c9e1c740eddec36b030
diff --git a/docs/genindex.html b/docs/genindex.html
index ef6fdce0ca..d415c18340 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -2527,6 +2527,8 @@
<li><a href="reference/api/python/relay/backend.html#tvm.relay.backend.vm.VMCompiler.lower">(tvm.relay.backend.vm.VMCompiler method)</a>
</li>
</ul></li>
+ <li><a href="reference/api/python/relay/backend.html#tvm.relay.backend.te_compiler.lower_to_primfunc">lower_to_primfunc() (in module tvm.relay.backend.te_compiler)</a>
+</li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.LowerCrossThreadReduction">LowerCrossThreadReduction() (in module tvm.tir.transform)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.LowerCustomDatatypes">LowerCustomDatatypes() (in module tvm.tir.transform)</a>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 64674c1736..adc9c09644 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ 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 12.614 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.543 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_keras.html b/docs/how_to/compile_models/from_keras.html
index 1747f4486e..71f55e8c3e 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 986ms/step
+1/1 [==============================] - 1s 1s/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 040fb915bf..8c7973f8a3 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ 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.zip02c6a30e-9341-42df-9b96-efa68a4c8f18 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.zip1280269e-c883-4cd9-baa7-37e3cc94bc30 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 2794651f1f..e2183395a0 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,14 +448,14 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<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, 46.0MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 47.8MB/s]
- 46%|####5 | 18.9M/41.5M [00:00<00:00, 44.5MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 40.9MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.8MB/s]
- 88%|########7 | 36.3M/41.5M [00:00<00:00, 44.6MB/s]
- 98%|#########7| 40.6M/41.5M [00:01<00:00, 33.1MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 40.0MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 63.0MB/s]
+ 30%|##9 | 12.3M/41.5M [00:00<00:00, 46.2MB/s]
+ 41%|#### | 17.0M/41.5M [00:00<00:00, 39.4MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.4MB/s]
+ 62%|######1 | 25.6M/41.5M [00:00<00:00, 30.8MB/s]
+ 77%|#######7 | 32.1M/41.5M [00:00<00:00, 38.6MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 40.6MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 39.5MB/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 d9f58959e3..60ef4dca98 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,12 +431,13 @@ be unstable.</p>
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]
- 14%|#4 | 6.30M/44.7M [00:00<00:00, 47.7MB/s]
- 32%|###2 | 14.3M/44.7M [00:00<00:00, 40.6MB/s]
- 54%|#####3 | 24.0M/44.7M [00:00<00:00, 52.9MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 55.0MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 61.9MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 54.9MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 63.0MB/s]
+ 32%|###2 | 14.4M/44.7M [00:00<00:00, 64.9MB/s]
+ 54%|#####3 | 24.0M/44.7M [00:00<00:00, 73.5MB/s]
+ 69%|######9 | 31.0M/44.7M [00:00<00:00, 69.2MB/s]
+ 84%|########4 | 37.6M/44.7M [00:00<00:00, 68.5MB/s]
+ 99%|#########8| 44.2M/44.7M [00:00<00:00, 66.3MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 67.9MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 05274c950f..9d4799f7d3 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ 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 13.723 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.184 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 05f098a887..d5ace7d944 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:53.913</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:09.422</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:13.723</p></td>
+<td><p>01:18.184</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:12.614</p></td>
+<td><p>01:15.543</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>00:48.130</p></td>
+<td><p>00:51.272</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>00:33.139</p></td>
+<td><p>00:34.135</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>00:29.266</p></td>
+<td><p>00:30.264</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:27.071</p></td>
+<td><p>00:28.407</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.754</p></td>
+<td><p>00:27.038</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>00:23.247</p></td>
+<td><p>00:24.055</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>00:18.467</p></td>
+<td><p>00:18.007</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>00:02.502</p></td>
+<td><p>00:02.516</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 8fecdc4ec9..06d652f44a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,9 +919,10 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2520.1820 2519.4955 2522.6710 2518.6284 1.3762
+ 3344.7055 3344.2562 3351.2438 3342.4476 2.4506
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.529 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/2387d8448da213eb625e6b3d916327d4/deploy_model_on_adreno.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_model_on_adreno.py</span></code></a></p>
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 448c47c13c..9de95162c5 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 17.1123 17.2048 17.3267 16.3535 0.2654
+ 17.2004 17.4280 17.7261 16.5236 0.4765
</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 eb18a517c8..09366e11e1 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,31 +453,26 @@ be unstable.</p>
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%|4 | 7.99M/170M [00:00<00:02, 61.3MB/s]
- 8%|8 | 14.3M/170M [00:00<00:02, 56.8MB/s]
- 12%|#1 | 19.7M/170M [00:00<00:03, 52.2MB/s]
- 15%|#5 | 26.0M/170M [00:00<00:02, 57.0MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:02, 51.3MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 60.1MB/s]
- 28%|##8 | 48.0M/170M [00:00<00:02, 54.8MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 52.8MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:02, 54.9MB/s]
- 44%|####3 | 74.1M/170M [00:01<00:01, 67.0MB/s]
- 48%|####7 | 81.0M/170M [00:01<00:01, 67.1MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 58.2MB/s]
- 57%|#####6 | 96.0M/170M [00:01<00:01, 56.3MB/s]
- 61%|######1 | 104M/170M [00:01<00:01, 61.4MB/s]
- 65%|######4 | 110M/170M [00:01<00:01, 62.1MB/s]
- 69%|######8 | 117M/170M [00:02<00:00, 64.2MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 64.4MB/s]
- 79%|#######9 | 134M/170M [00:02<00:00, 63.6MB/s]
- 83%|########2 | 140M/170M [00:02<00:00, 57.7MB/s]
- 86%|########5 | 146M/170M [00:02<00:00, 49.6MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 47.8MB/s]
- 93%|#########3| 158M/170M [00:02<00:00, 48.9MB/s]
- 96%|#########6| 163M/170M [00:03<00:00, 44.0MB/s]
- 99%|#########8| 168M/170M [00:03<00:00, 39.6MB/s]
-100%|##########| 170M/170M [00:03<00:00, 54.6MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:01, 113MB/s]
+ 15%|#4 | 25.1M/170M [00:00<00:01, 76.2MB/s]
+ 19%|#9 | 32.8M/170M [00:00<00:02, 65.5MB/s]
+ 25%|##4 | 42.1M/170M [00:00<00:01, 74.3MB/s]
+ 29%|##9 | 49.6M/170M [00:00<00:02, 58.9MB/s]
+ 36%|###5 | 60.6M/170M [00:00<00:01, 72.7MB/s]
+ 40%|#### | 68.4M/170M [00:01<00:01, 64.2MB/s]
+ 46%|####6 | 78.3M/170M [00:01<00:01, 61.7MB/s]
+ 51%|##### | 86.3M/170M [00:01<00:01, 65.8MB/s]
+ 56%|#####5 | 94.3M/170M [00:01<00:01, 61.5MB/s]
+ 59%|#####9 | 101M/170M [00:01<00:01, 49.0MB/s]
+ 62%|######2 | 106M/170M [00:01<00:01, 42.9MB/s]
+ 70%|######9 | 119M/170M [00:01<00:00, 61.6MB/s]
+ 75%|#######5 | 128M/170M [00:02<00:00, 68.7MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 62.1MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 66.2MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 66.6MB/s]
+ 95%|#########5| 161M/170M [00:02<00:00, 74.4MB/s]
+ 99%|#########9| 169M/170M [00:02<00:00, 63.3MB/s]
+100%|##########| 170M/170M [00:02<00:00, 64.1MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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=& [...]
@@ -575,7 +570,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 23.871 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 35.974 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 29e7b1d9c3..a72ef7075f 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,10 +497,10 @@ training. Other models require a full post training calibration.</p>
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]
- 47%|####6 | 6.30M/13.6M [00:00<00:00, 31.9MB/s]
- 69%|######8 | 9.34M/13.6M [00:00<00:00, 28.8MB/s]
- 90%|########9 | 12.2M/13.6M [00:00<00:00, 24.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 28.6MB/s]
+ 47%|####6 | 6.30M/13.6M [00:00<00:00, 38.8MB/s]
+ 74%|#######3 | 10.0M/13.6M [00:00<00:00, 37.1MB/s]
+100%|#########9| 13.5M/13.6M [00:00<00:00, 35.7MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 36.4MB/s]
</pre></div>
</div>
</div>
@@ -591,7 +591,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.6430 90.5211 94.4103 90.0929 0.6280
+ 90.6887 90.6066 92.3708 90.2499 0.3538
</pre></div>
</div>
<div class="admonition note">
@@ -630,7 +630,7 @@ 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 8.265 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.756 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 5af34a566c..b3a18b1111 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.9839 119.8273 123.2217 118.6827 0.7435
+ 121.5437 121.5220 127.4966 120.0875 0.9109
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ 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> ( 2 minutes 25.273 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.589 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 36d099896e..b9a9ac08bf 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ 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 42.158 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 44.935 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 fa957b7d5d..85a03d7993 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,22 +462,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|5 | 7228/132723 [00:00<00:01, 72268.87KB/s]
- 12%|#2 | 15952/132723 [00:00<00:01, 81072.29KB/s]
- 19%|#8 | 24708/132723 [00:00<00:01, 84031.76KB/s]
- 25%|##5 | 33479/132723 [00:00<00:01, 85479.90KB/s]
- 32%|###1 | 42258/132723 [00:00<00:01, 86310.17KB/s]
- 38%|###8 | 51029/132723 [00:00<00:00, 86782.32KB/s]
- 45%|####5 | 59738/132723 [00:00<00:00, 86881.37KB/s]
- 52%|#####1 | 68527/132723 [00:00<00:00, 87199.50KB/s]
- 58%|#####8 | 77286/132723 [00:00<00:00, 87318.40KB/s]
- 65%|######4 | 86018/132723 [00:01<00:00, 75419.08KB/s]
- 71%|#######1 | 94689/132723 [00:01<00:00, 78529.65KB/s]
- 78%|#######7 | 103341/132723 [00:01<00:00, 80784.43KB/s]
- 84%|########4 | 112061/132723 [00:01<00:00, 82626.45KB/s]
- 91%|######### | 120716/132723 [00:01<00:00, 83766.04KB/s]
- 97%|#########7| 129317/132723 [00:01<00:00, 84422.61KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 83338.25KB/s]
+ 4%|3 | 4765/132723 [00:00<00:02, 47640.16KB/s]
+ 9%|9 | 12284/132723 [00:00<00:01, 63841.38KB/s]
+ 15%|#5 | 20245/132723 [00:00<00:01, 71037.92KB/s]
+ 21%|##1 | 28039/132723 [00:00<00:01, 73759.28KB/s]
+ 27%|##7 | 35937/132723 [00:00<00:01, 75639.91KB/s]
+ 33%|###3 | 43866/132723 [00:00<00:01, 76878.27KB/s]
+ 39%|###8 | 51591/132723 [00:00<00:01, 76997.89KB/s]
+ 45%|####4 | 59291/132723 [00:00<00:00, 76505.44KB/s]
+ 50%|##### | 66943/132723 [00:00<00:00, 75997.90KB/s]
+ 56%|#####6 | 74544/132723 [00:01<00:00, 75859.19KB/s]
+ 62%|######1 | 82131/132723 [00:01<00:00, 75563.67KB/s]
+ 68%|######7 | 89688/132723 [00:01<00:00, 75250.46KB/s]
+ 73%|#######3 | 97214/132723 [00:01<00:00, 75018.69KB/s]
+ 79%|#######8 | 104717/132723 [00:01<00:00, 74703.44KB/s]
+ 85%|########4 | 112188/132723 [00:01<00:00, 73632.65KB/s]
+ 90%|######### | 119555/132723 [00:01<00:00, 73446.02KB/s]
+ 96%|#########5| 126912/132723 [00:01<00:00, 73479.56KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 73779.67KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -516,7 +518,7 @@ 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> ( 3 minutes 10.982 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> ( 3 minutes 19.080 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 2b36845602..82470e0259 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>14:09.445</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:58.233</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:23.871</p></td>
+<td><p>03:35.974</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>03:10.982</p></td>
+<td><p>03:19.080</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>02:25.273</p></td>
+<td><p>02:32.589</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>01:42.158</p></td>
+<td><p>01:44.935</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>01:08.265</p></td>
+<td><p>01:10.756</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:51.722</p></td>
+<td><p>01:02.529</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:36.634</p></td>
+<td><p>00:38.496</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:25.559</p></td>
+<td><p>00:27.048</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.973</p></td>
+<td><p>00:26.820</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index fa3dadf69c..5d448ffcd0 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ 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.zip0c9ce879-6ac9-4da0-a888-956a05311c3f 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.zipe58f0129-2794-4194-8ac9-91ff29a821b4 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 d67541a635..e6ceeedb59 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:48.625</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:50.865</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:45.094</p></td>
+<td><p>00:47.138</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>00:02.467</p></td>
+<td><p>00:02.613</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>00:01.055</p></td>
+<td><p>00:01.104</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 9a82735ea2..ee9bce361e 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ 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: 7371us [7371us] (46.76%; 46.76%)
-FoldScaleAxis: 8394us [9us] (53.24%; 53.24%)
- FoldConstant: 8385us [1696us] (53.19%; 99.90%)
- InferType: 6689us [6689us] (42.43%; 79.77%)
+InferType: 7798us [7798us] (46.60%; 46.60%)
+FoldScaleAxis: 8937us [10us] (53.40%; 53.40%)
+ FoldConstant: 8927us [1854us] (53.34%; 99.89%)
+ InferType: 7072us [7072us] (42.26%; 79.23%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ 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: 6753us [6753us] (44.93%; 44.93%)
-FoldScaleAxis: 8276us [5us] (55.07%; 55.07%)
- FoldConstant: 8271us [1690us] (55.03%; 99.94%)
- InferType: 6581us [6581us] (43.79%; 79.56%)
+InferType: 7066us [7066us] (44.29%; 44.29%)
+FoldScaleAxis: 8887us [8us] (55.71%; 55.71%)
+ FoldConstant: 8879us [1759us] (55.66%; 99.91%)
+ InferType: 7119us [7119us] (44.63%; 80.18%)
</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 efa2f028f4..6f2f99e0eb 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ 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: 43.208671 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 41.493152 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 a8d5db193f..1eeaed652f 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ 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: 13.363766 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.915680 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 1a0b9a5a28..d2bc1349df 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ 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: 0.019119
-Baseline: 3.291093
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019706
+Baseline: 3.558644
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ 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: 0.313798
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.339654
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ 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: 0.348404
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.359926
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ 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: 0.117668
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.143151
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ 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: 0.109544
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110794
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ 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: 0.112521
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.113632
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ 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: 0.147766
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.150467
</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 70048a0136..1b7eacfdbe 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:34.989</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:36.852</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</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>00:32.416</p></td>
+<td><p>00:34.225</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>00:01.521</p></td>
+<td><p>00:01.543</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.051</p></td>
+<td><p>00:01.085</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 f09dcfbfc0..caaecff096 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>09:12.158</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:30.178</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</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>05:42.632</p></td>
+<td><p>05:53.358</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>01:33.260</p></td>
+<td><p>01:36.872</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>01:02.661</p></td>
+<td><p>01:04.523</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>00:29.806</p></td>
+<td><p>00:30.452</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:12.342</p></td>
+<td><p>00:12.779</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:11.457</p></td>
+<td><p>00:12.194</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 03d2817213..40659e2d1b 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
@@ -503,679 +503,159 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 128;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[15] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
- let cse_var_1: int32 = (rc.outer.outer*196)
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((cse_var_1 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_1 < 30), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data_3[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*16)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*16), 81)) && (floormod((threadIdx.x_1*16), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv((threadIdx.x_1*16), 81)*49)) + (floordiv(floormod((threadIdx.x_1*16), 81), [...]
+ pad_temp.shared_1[((threadIdx.x_1*16) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 1), 81)) && (floormod(((threadIdx.x_1*16) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 2), 81)) && (floormod(((threadIdx.x_1*16) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 3), 81)) && (floormod(((threadIdx.x_1*16) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 4)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 4), 81)) && (floormod(((threadIdx.x_1*16) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 4), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 5)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 5), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 6)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 6), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 7)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 7), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 8)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 8), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 9), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*16) + 10)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 10), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dt [...]
+ pad_temp.shared_1[((threadIdx.x_1*16) + 11)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 11), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dt [...]
+ pad_temp.shared_1[((threadIdx.x_1*16) + 12)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 12), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dt [...]
+ pad_temp.shared_1[((threadIdx.x_1*16) + 13)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 13), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dt [...]
+ pad_temp.shared_1[((threadIdx.x_1*16) + 14)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 14), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dt [...]
+ pad_temp.shared_1[((threadIdx.x_1*16) + 15)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 15), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dt [...]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[(threadIdx.x_2*16)] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod((threadIdx.x_2*16), 36), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 784)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 55), 81)) && (floormod(((threadIdx.x_1*16) + 55), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 784), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 55), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 1)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 1), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 785)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 56), 81)) && (floormod(((threadIdx.x_1*16) + 56), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 785), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 56), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 2)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 2), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 786)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 57), 81)) && (floormod(((threadIdx.x_1*16) + 57), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 786), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 57), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 3)] = kernel_3[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 787)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 58), 81)) && (floormod(((threadIdx.x_1*16) + 58), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 787), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 58), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 4)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 4), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 788)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 59), 81)) && (floormod(((threadIdx.x_1*16) + 59), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 788), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 59), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 5)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 5), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 789)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 60), 81)) && (floormod(((threadIdx.x_1*16) + 60), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 789), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 60), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 6)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 790)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 61), 81)) && (floormod(((threadIdx.x_1*16) + 61), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 790), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 61), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 7)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 7), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 791)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 62), 81)) && (floormod(((threadIdx.x_1*16) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 791), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 62), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 8)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 8), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 792)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)) && (floormod(((threadIdx.x_1*16) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 792), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 9)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 793)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 64), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 793), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)*7)) + floormod(((threadIdx.x_1 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 10)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 10), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 794)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 65), 81)) && (floormod(((threadIdx.x_1*16) + 65), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 794), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 65), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 11)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 11), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 795)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 66), 81)) && (floormod(((threadIdx.x_1*16) + 66), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 795), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 66), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 12)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 796)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 67), 81)) && (floormod(((threadIdx.x_1*16) + 67), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 796), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 67), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 13)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 13), 36), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 797)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 68), 81)) && (floormod(((threadIdx.x_1*16) + 68), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 797), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 68), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 14)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floordiv(floormod(((threadIdx.x_2*16) + 14), 36), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 798)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 69), 81)) && (floormod(((threadIdx.x_1*16) + 69), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 798), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 69), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32 [...]
}
- if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*16) + 15)] = kernel_3[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*36)) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 12)*3)) + floormod(threadIdx.x_2, 3))]
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*16) + 799)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 70), 81)) && (floormod(((threadIdx.x_1*16) + 70), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data_3[((((cse_var_2 + (floordiv(((threadIdx.x_1*16) + 799), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 70), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32 [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((blockIdx.x*18432) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 49)] = kernel_3[((((blockIdx.x*18432) + cse_var_1) + (floordiv((threadIdx.x_2 + 49), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 98), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 98), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 147)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 147), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 1)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 196), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 245)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 245), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 101), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 294), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 343)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 343), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 55), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 441)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 441), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 490), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 58), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_2 < 37), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 539)] = kernel_3[(((((blockIdx.x*18432) + (floordiv((threadIdx.x_2 + 539), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 107), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.inner: int32, 0, 16) {
+ let cse_var_3: int32 = (rc.inner*9)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_3]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 288)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_3 + 432)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 289)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 145)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_3 + 433)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 290)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 146)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_3 + 434)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 291)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 147)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_3 + 435)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 292)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 148)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_3 + 436)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 293)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 149)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_3 + 437)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 294)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 150)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_3 + 438)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 295)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 151)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_3 + 439)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 296)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 152)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_3 + 440)]))
}
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[144]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[288]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[432]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[3]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[147]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[291]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[435]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[6]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[150]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[294]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[438]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[36]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[180]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[324]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[468]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[39]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[183]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[327]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[471]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[42]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[186]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[330]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[474]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[72]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[216]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[360]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[504]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[75]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[219]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[363]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[507]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[78]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[222]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[366]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[510]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[108]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[252]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[396]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[540]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[111]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[255]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[399]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[543]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[114]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[258]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[402]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[546]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[145]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[289]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[433]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[4]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[148]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[292]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[436]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[7]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[151]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[295]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[439]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[37]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[181]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[325]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[469]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[40]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[184]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[328]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[472]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[43]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[187]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[331]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[475]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[73]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[217]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[361]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[505]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[76]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[220]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[364]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[508]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[79]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[223]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[367]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[511]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[109]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[253]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[397]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[541]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[112]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[256]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[400]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[544]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[115]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[259]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[403]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[547]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[146]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[290]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[434]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[5]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[149]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[293]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[437]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[8]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[152]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[296]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[440]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[38]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[182]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[326]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[470]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[41]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[185]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[329]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[473]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[44]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[188]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[332]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[476]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[74]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[218]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[362]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[506]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[77]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[221]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[365]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[509]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[80]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[224]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[368]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[512]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[110]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[254]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[398]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[542]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[113]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[257]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[401]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[545]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[116]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[260]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[404]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[548]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[9]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[153]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[297]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[441]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[12]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[156]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[300]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[444]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[15]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[159]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[303]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[447]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[45]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[189]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[333]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[477]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[48]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[192]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[336]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[480]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[51]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[195]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[339]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[483]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[81]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[225]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[369]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[513]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[84]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[228]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[372]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[516]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[87]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[231]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[375]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[519]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[117]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[261]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[405]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[549]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[120]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[264]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[408]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[552]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[123]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[267]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[411]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[555]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[10]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[154]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[298]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[442]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[13]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[157]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[301]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[445]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[16]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[160]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[304]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[448]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[46]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[190]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[334]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[478]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[49]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[193]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[337]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[481]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[52]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[196]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[340]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[484]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[82]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[226]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[370]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[514]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[85]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[229]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[373]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[517]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[88]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[232]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[376]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[520]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[118]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[262]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[406]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[550]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[121]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[265]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[409]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[553]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[124]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[268]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[412]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[556]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[11]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[155]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[299]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[443]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[14]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[158]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[302]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[446]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[17]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[161]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[305]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[449]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[47]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[191]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[335]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[479]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[50]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[194]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[338]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[482]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[53]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[197]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[341]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[485]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[83]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[227]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[371]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[515]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[86]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[230]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[374]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[518]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[89]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[233]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[377]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[521]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[119]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[263]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[407]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[551]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[122]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[266]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[410]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[554]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[125]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[269]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[413]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[557]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[18]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[162]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[306]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[450]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[21]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[165]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[309]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[453]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[24]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[168]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[312]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[456]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[54]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[198]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[342]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[486]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[57]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[201]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[345]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[489]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[60]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[204]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[348]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[492]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[90]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[234]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[378]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[522]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[93]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[237]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[381]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[525]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[96]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[240]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[384]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[528]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[126]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[270]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[414]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[558]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[129]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[273]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[417]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[561]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[132]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[276]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[420]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[564]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[19]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[163]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[307]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[451]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[22]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[166]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[310]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[454]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[25]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[169]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[313]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[457]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[55]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[199]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[343]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[487]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[58]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[202]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[346]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[490]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[61]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[205]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[349]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[493]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[91]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[235]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[379]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[523]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[94]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[238]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[382]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[526]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[97]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[241]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[385]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[529]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[127]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[271]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[415]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[559]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[130]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[274]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[418]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[562]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[133]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[277]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[421]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[565]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[20]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[164]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[308]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[452]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[23]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[167]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[311]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[455]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[26]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[170]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[314]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[458]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[56]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[200]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[344]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[488]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[59]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[203]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[347]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[491]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[62]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[206]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[350]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[494]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[92]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[236]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[380]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[524]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[95]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[239]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[383]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[527]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[98]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[242]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[386]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[530]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[128]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[272]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[416]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[560]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[131]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[275]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[419]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[563]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[134]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[278]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[422]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[566]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[27]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[171]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[315]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[459]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[30]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[174]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[318]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[462]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[33]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[177]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[321]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[465]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[63]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[207]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[351]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[495]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[66]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[210]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[354]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[498]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[69]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[213]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[357]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[501]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[99]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[243]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[387]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[531]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[102]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[246]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[390]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[534]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[105]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[249]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[393]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[537]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[135]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[279]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[423]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[567]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[138]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[282]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[426]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[570]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[141]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[285]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[429]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[573]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[28]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[172]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[316]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[460]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[31]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[175]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[319]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[463]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[34]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[178]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[322]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[466]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[64]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[208]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[352]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[496]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[67]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[211]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[355]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[499]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[70]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[214]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[358]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[502]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[100]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[244]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[388]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[532]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[103]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[247]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[391]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[535]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[106]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[250]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[394]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[538]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[136]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[280]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[424]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[568]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[139]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[283]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[427]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[571]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[142]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[286]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[430]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[574]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[29]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[173]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[317]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[461]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[32]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[176]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[320]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[464]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[35]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[179]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[323]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[467]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[65]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[209]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[353]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[497]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[68]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[212]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[356]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[500]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[71]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[215]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[359]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[503]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[101]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[245]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[389]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[533]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[104]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[248]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[392]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[536]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[107]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[251]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[395]))
- conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[539]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[137]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[281]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[425]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[569]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[140]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[284]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[428]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[572]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[143]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[287]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[431]))
- conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[575]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*16) + i1.inner)]), 0f32)
- compute_3[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[(((blockIdx.x*16) + i1.inner) + 4)]), 0f32)
- compute_3[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 392)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias_3[(((blockIdx.x*16) + i1.inner) + 8)]), 0f32)
- compute_3[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 588)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias_3[(((blockIdx.x*16) + i1.inner) + 12)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*4) + i1.inner)]), 0f32)
+ compute_3[((((blockIdx.x*196) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias_3[(((blockIdx.x*4) + i1.inner) + 2)]), 0f32)
}
}
}
@@ -1212,7 +692,7 @@ 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: 0.288 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.326 ms
</pre></div>
</div>
</div>
@@ -1241,10 +721,10 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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)
@@ -1253,19 +733,19 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+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)
@@ -1288,16 +768,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=16)
+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=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+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=16)
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=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1316,667 +796,136 @@ CUDA source code:
#define uint64_t unsigned long long
#endif
extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[324];
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[1296];
__shared__ float kernel_shared[576];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 30) {
- pad_temp_shared[(((int)threadIdx.x) + 294)] = ((((((int)threadIdx.x) < 21) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 294) / 81) * 49)) + (((((int)threadIdx.x) + 51) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((9 <= ((((int)threadIdx.x) * 16) % 81)) && (((((int)threadIdx.x) * 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 16) / 81) * 49)) + ((((((int)threadIdx.x) * 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((9 <= (((((int)threadIdx.x) * 16) + 1) % 81)) && ((((((int)threadIdx.x) * 16) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((9 <= (((((int)threadIdx.x) * 16) + 2) % 81)) && ((((((int)threadIdx.x) * 16) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((9 <= (((((int)threadIdx.x) * 16) + 3) % 81)) && ((((((int)threadIdx.x) * 16) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((9 <= (((((int)threadIdx.x) * 16) + 4) % 81)) && ((((((int)threadIdx.x) * 16) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 4) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 5) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 6) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 7) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 8) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 9) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 10) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 11) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 12) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 13) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 14) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 15) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 784)] = (((((9 <= (((((int)threadIdx.x) * 16) + 55) % 81)) && ((((((int)threadIdx.x) * 16) + 55) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 784) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 55) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[(((int)threadIdx.x) * 16)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) * 16) % 36) / 3) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 785)] = (((((9 <= (((((int)threadIdx.x) * 16) + 56) % 81)) && ((((((int)threadIdx.x) * 16) + 56) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 785) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 56) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 1) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 786)] = (((((9 <= (((((int)threadIdx.x) * 16) + 57) % 81)) && ((((((int)threadIdx.x) * 16) + 57) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 786) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 57) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 2) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 787)] = (((((9 <= (((((int)threadIdx.x) * 16) + 58) % 81)) && ((((((int)threadIdx.x) * 16) + 58) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 787) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 58) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 788)] = (((((9 <= (((((int)threadIdx.x) * 16) + 59) % 81)) && ((((((int)threadIdx.x) * 16) + 59) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 788) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 59) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 4) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 789)] = (((((9 <= (((((int)threadIdx.x) * 16) + 60) % 81)) && ((((((int)threadIdx.x) * 16) + 60) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 789) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 60) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 5) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 790)] = (((((9 <= (((((int)threadIdx.x) * 16) + 61) % 81)) && ((((((int)threadIdx.x) * 16) + 61) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 790) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 61) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 791)] = (((((9 <= (((((int)threadIdx.x) * 16) + 62) % 81)) && ((((((int)threadIdx.x) * 16) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 791) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 7) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 792)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 16) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 792) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 8) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 793)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 64) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 793) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - [...]
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 794)] = (((((9 <= (((((int)threadIdx.x) * 16) + 65) % 81)) && ((((((int)threadIdx.x) * 16) + 65) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 794) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 65) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 10) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 795)] = (((((9 <= (((((int)threadIdx.x) * 16) + 66) % 81)) && ((((((int)threadIdx.x) * 16) + 66) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 795) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 66) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 11) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 796)] = (((((9 <= (((((int)threadIdx.x) * 16) + 67) % 81)) && ((((((int)threadIdx.x) * 16) + 67) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 796) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 67) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 797)] = (((((9 <= (((((int)threadIdx.x) * 16) + 68) % 81)) && ((((((int)threadIdx.x) * 16) + 68) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 797) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 68) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 13) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 798)] = (((((9 <= (((((int)threadIdx.x) * 16) + 69) % 81)) && ((((((int)threadIdx.x) * 16) + 69) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 798) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 69) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) + 14) % 36) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 799)] = (((((9 <= (((((int)threadIdx.x) * 16) + 70) % 81)) && ((((((int)threadIdx.x) * 16) + 70) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 799) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 70) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 36) {
- kernel_shared[((((int)threadIdx.x) * 16) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 18432) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 49) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 98) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 147) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 3)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 52) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 101) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 343)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 343) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 55) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 441)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 441) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9)];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 58) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 37) {
+ kernel_shared[(((int)threadIdx.x) + 539)] = kernel[(((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 539) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 107) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[144]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[288]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[432]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[3]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[147]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[291]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[435]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[6]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[150]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[294]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[438]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[36]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[180]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[324]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[468]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[39]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[183]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[327]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[471]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[42]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[186]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[330]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[474]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[72]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[216]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[360]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[504]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[75]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[219]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[363]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[507]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[78]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[222]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[366]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[510]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[108]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[252]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[396]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[540]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[111]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[255]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[399]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[543]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[114]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[258]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[402]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[546]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[145]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[289]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[433]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[4]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[148]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[292]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[436]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[7]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[151]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[295]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[439]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[37]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[181]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[325]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[469]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[40]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[184]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[328]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[472]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[43]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[187]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[331]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[475]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[73]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[217]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[361]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[505]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[76]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[220]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[364]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[508]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[79]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[223]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[367]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[511]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[109]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[253]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[397]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[541]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[112]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[256]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[400]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[544]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[115]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[259]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[403]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[547]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[146]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[290]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[434]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[5]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[149]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[293]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[437]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[8]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[152]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[296]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[440]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[38]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[182]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[326]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[470]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[41]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[185]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[329]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[473]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[44]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[188]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[332]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[476]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[74]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[218]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[362]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[506]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[77]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[221]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[365]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[509]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[80]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[224]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[368]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[512]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[110]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[254]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[398]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[542]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[113]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[257]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[401]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[545]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[116]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[260]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[404]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[548]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[9]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[153]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[297]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[441]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[12]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[156]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[300]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[444]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[15]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[159]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[303]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[447]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[45]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[189]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[333]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[477]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[48]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[192]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[336]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[480]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[51]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[195]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[339]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[483]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[81]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[225]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[369]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[513]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[84]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[228]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[372]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[516]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[87]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[231]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[375]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[519]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[117]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[261]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[405]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[549]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[120]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[264]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[408]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[552]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[123]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[267]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[411]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[555]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[10]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[154]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[298]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[442]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[13]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[157]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[301]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[445]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[16]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[160]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[304]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[448]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[46]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[190]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[334]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[478]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[49]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[193]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[337]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[481]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[52]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[196]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[340]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[484]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[82]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[226]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[370]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[514]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[85]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[229]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[373]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[517]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[88]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[232]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[376]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[520]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[118]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[262]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[406]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[550]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[121]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[265]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[409]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[553]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[124]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[268]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[412]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[556]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[11]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[155]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[299]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[443]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[14]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[158]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[302]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[446]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[17]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[161]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[305]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[449]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[47]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[191]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[335]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[479]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[50]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[194]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[338]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[482]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[53]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[197]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[341]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[485]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[83]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[227]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[371]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[515]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[86]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[230]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[374]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[518]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[89]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[233]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[377]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[521]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[119]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[263]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[407]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[551]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[122]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[266]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[410]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[554]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[125]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[269]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[413]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[557]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[18]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[162]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[306]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[450]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[21]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[165]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[309]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[453]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[24]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[168]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[312]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[456]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[54]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[198]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[342]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[486]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[57]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[201]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[345]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[489]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[60]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[204]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[348]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[492]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[90]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[234]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[378]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[522]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[93]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[237]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[381]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[525]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[96]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[240]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[384]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[528]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[126]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[270]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[414]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[558]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[129]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[273]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[417]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[561]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[132]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[276]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[420]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[564]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[19]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[163]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[307]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[451]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[22]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[166]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[310]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[454]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[25]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[169]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[313]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[457]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[55]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[199]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[343]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[487]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[58]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[202]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[346]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[490]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[61]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[205]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[349]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[493]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[91]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[235]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[379]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[523]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[94]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[238]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[382]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[526]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[97]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[241]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[385]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[529]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[127]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[271]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[415]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[559]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[130]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[274]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[418]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[562]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[133]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[277]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[421]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[565]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[20]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[164]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[308]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[452]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[23]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[167]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[311]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[455]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[26]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[170]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[314]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[458]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[56]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[200]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[344]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[488]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[59]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[203]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[347]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[491]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[62]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[206]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[350]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[494]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[92]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[236]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[380]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[524]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[95]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[239]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[383]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[527]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[98]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[242]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[386]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[530]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[128]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[272]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[416]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[560]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[131]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[275]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[419]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[563]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[134]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[278]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[422]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[566]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[27]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[171]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[315]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[459]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[30]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[174]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[318]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[462]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[33]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[177]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[321]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[465]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[63]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[207]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[351]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[495]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[66]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[210]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[354]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[498]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[69]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[213]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[357]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[501]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[99]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[243]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[387]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[531]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[102]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[246]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[390]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[534]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[105]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[249]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[393]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[537]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[135]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[279]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[423]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[567]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[138]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[282]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[426]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[570]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[141]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[285]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[429]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[573]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[28]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[172]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[316]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[460]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[31]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[175]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[319]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[463]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[34]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[178]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[322]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[466]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[64]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[208]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[352]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[496]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[67]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[211]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[355]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[499]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[70]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[214]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[358]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[502]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[100]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[244]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[388]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[532]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[103]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[247]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[391]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[535]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[106]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[250]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[394]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[538]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[136]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[280]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[424]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[568]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[139]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[283]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[427]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[571]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[142]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[286]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[430]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[574]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[29]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[173]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[317]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[461]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[32]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[176]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[320]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[464]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[35]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[179]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[323]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[467]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[65]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[209]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[353]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[497]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[68]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[212]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[356]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[500]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[71]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[215]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[359]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[503]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[101]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[245]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[389]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[533]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[104]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[248]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[392]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[536]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[107]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[251]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[395]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[539]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[137]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[281]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[425]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[569]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[140]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[284]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[428]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[572]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[143]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[287]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[431]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[575]));
+ for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_inner * 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 288)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_inner * 9) + 432)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 289)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_inner * 9) + 433)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 290)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_inner * 9) + 434)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 291)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_inner * 9) + 435)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 292)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_inner * 9) + 436)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 293)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_inner * 9) + 437)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 294)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_inner * 9) + 438)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 295)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_inner * 9) + 439)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 296)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_inner * 9) + 440)]));
+ }
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
}
}
</pre></div>
@@ -2013,7 +962,7 @@ 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> ( 5 minutes 42.632 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 53.358 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 bc5bb7f8f3..11ae657076 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ 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)
- 7.8963 7.8910 7.9117 7.8861 0.0111
+ 7.8843 7.8850 7.8855 7.8822 0.0014
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ 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 2.661 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.523 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_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_network_cuda.py</span></code></a></p>
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 907deb2e5a..d1fa6edb52 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ 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)
- 769.0901 768.2937 770.8430 768.1336 1.2412
+ 798.6117 796.5761 804.8121 794.4470 4.4696
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ 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 33.260 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.872 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 196b95c36a..d42aff9127 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,27 +632,77 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
for (i.outer.inner: int32, 0, 16) {
for (nb_j.inner: int32, 0, 2) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [4096], [])[cse_var_1] = 0f32
+ compute_4[(cse_var_1 + 1)] = 0f32
+ compute_4[(cse_var_1 + 2)] = 0f32
+ compute_4[(cse_var_1 + 3)] = 0f32
+ compute_4[(cse_var_1 + 4)] = 0f32
+ compute_4[(cse_var_1 + 5)] = 0f32
+ compute_4[(cse_var_1 + 6)] = 0f32
+ compute_4[(cse_var_1 + 7)] = 0f32
+ compute_4[(cse_var_1 + 8)] = 0f32
+ compute_4[(cse_var_1 + 9)] = 0f32
+ compute_4[(cse_var_1 + 10)] = 0f32
+ compute_4[(cse_var_1 + 11)] = 0f32
+ compute_4[(cse_var_1 + 12)] = 0f32
+ compute_4[(cse_var_1 + 13)] = 0f32
+ compute_4[(cse_var_1 + 14)] = 0f32
+ compute_4[(cse_var_1 + 15)] = 0f32
+ }
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_2: int32 = (((i.outer.inner*32) + (nb_j.inner*16)) + j)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_20]*16) + cse_var_21)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_19 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder_17[(cse_var_19 + placeholder_18[(placeholder_15[cse_var_20] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
- compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_4]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -690,7 +740,7 @@ 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: 2.215 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.877 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 339d92f90f..8d86a1bdf5 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:41.200</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:32.925</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,18 +349,18 @@
</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>00:41.164</p></td>
+<td><p>00:32.886</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.023</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 118834282a..8e8697a23d 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,7 +689,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4335673
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1250330
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -812,8 +812,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6639821
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2243359
+No: 3 GFLOPS: 137.13/137.13 result: MeasureResult(costs=(0.001688228484375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8228330612182617, timestamp=1671007996.2653587) [('tile_f', [-1, 8, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2035242
+No: 4 GFLOPS: 0.00/137.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -935,9 +936,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3120208
-No: 4 GFLOPS: 2.03/2.03 result: MeasureResult(costs=(0.11384416950000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.947231769561768, timestamp=1670956837.3610103) [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4960400
-No: 5 GFLOPS: 0.00/2.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5935863
+No: 5 GFLOPS: 0.00/137.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1059,8 +1059,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 512, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8305009
-No: 6 GFLOPS: 0.00/2.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8861027
+No: 6 GFLOPS: 293.95/293.95 result: MeasureResult(costs=(0.0007875517784810127,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.497633218765259, timestamp=1671007999.9878116) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10076014
+No: 7 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1182,9 +1183,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6949955
-No: 7 GFLOPS: 328.23/328.23 result: MeasureResult(costs=(0.000705303540229885,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4255976676940918, timestamp=1670956839.9784958) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10104172
-No: 8 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,472548
+No: 8 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1306,8 +1306,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5369278
-No: 9 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7273113
+No: 9 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1429,8 +1429,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4831392
-No: 10 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7718880
+No: 10 GFLOPS: 20.44/293.95 result: MeasureResult(costs=(0.011325489444444444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2964777946472168, timestamp=1671008002.5026994) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6589441
+No: 11 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1552,9 +1553,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5582594
-No: 11 GFLOPS: 8.22/328.23 result: MeasureResult(costs=(0.0281544475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.20864200592041, timestamp=1670956843.4195638) [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3717727
-No: 12 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5577743
+No: 12 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1676,8 +1676,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5394013
-No: 13 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4405992
+No: 13 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1799,8 +1799,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1445666
-No: 14 GFLOPS: 0.00/328.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8740001
+No: 14 GFLOPS: 31.31/293.95 result: MeasureResult(costs=(0.007393682142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2788639068603516, timestamp=1671008005.121807) [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5879075
+No: 15 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1922,9 +1923,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3342585
-No: 15 GFLOPS: 437.31/437.31 result: MeasureResult(costs=(0.0005293790394736843,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8600027561187744, timestamp=1670956845.514734) [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8809357
-No: 16 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2598122
+No: 16 GFLOPS: 2.46/293.95 result: MeasureResult(costs=(0.0942582855,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.017066717147827, timestamp=1671008006.7710116) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2209904
+No: 17 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2046,8 +2047,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,503824
-No: 17 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10162174
+No: 18 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2169,8 +2170,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5360249
-No: 18 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5912159
+No: 19 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2292,26 +2293,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6752374
-No: 19 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,455347
-No: 20 GFLOPS: 0.00/437.31 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1275280
+No: 20 GFLOPS: 0.00/293.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2433,7 +2416,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8474203
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8954779
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2472,9 +2455,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8809357
+[('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10076014
Finish loading 20 records
-Time cost of this operator: 0.000876
+Time cost of this operator: 0.000993
</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 a4fbcca73b..0248d0a8d5 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -598,10 +598,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## 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 312.0 98.723 (1, 2, 10, 10, 3) 2 1 [312.0]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.048 0.965 (1, 6, 10, 10) 1 1 [3.048]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.987 0.312 (1, 1, 10, 10, 3) 1 1 [0.987]
-Total_time - 316.035 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.706 (1, 2, 10, 10, 3) 2 1 [309.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.057 0.975 (1, 6, 10, 10) 1 1 [3.057]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.001 0.319 (1, 1, 10, 10, 3) 1 1 [1.001]
+Total_time - 313.658 - - - - -
</pre></div>
</div>
</div>
@@ -653,10 +653,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 135.5 97.813 (1, 6, 10, 10, 1) 2 1 [135.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.053 1.482 (1, 6, 10, 10) 1 1 [2.053]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.705 (1, 1, 10, 10, 3) 1 1 [0.976]
-Total_time - 138.53 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 108.1 97.532 (1, 6, 10, 10, 1) 2 1 [108.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 1.594 (1, 6, 10, 10) 1 1 [1.767]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.874 (1, 1, 10, 10, 3) 1 1 [0.969]
+Total_time - 110.835 - - - - -
</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_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 3414def4e0..aa1d949d36 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,7 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 42.3MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 44.5MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -564,7 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.313 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.774 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_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">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 3ad162fc68..371255e24a 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ 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/tmp_90n_aec/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp31ymcrcs/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ 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], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp_90n_aec/images/target contains 8144 images
-/tmp/tmp_90n_aec/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [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/tmp31ymcrcs/images/target contains 8144 images
+/tmp/tmp31ymcrcs/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ 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 - 47s - loss: 0.2193 - accuracy: 0.9270 - val_loss: 0.1186 - val_accuracy: 0.9554 - 47s/epoch - 145ms/step
+328/328 - 48s - loss: 0.2307 - accuracy: 0.9188 - val_loss: 0.1351 - val_accuracy: 0.9573 - 48s/epoch - 146ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.1000 - accuracy: 0.9647 - val_loss: 0.1079 - val_accuracy: 0.9592 - 44s/epoch - 133ms/step
+328/328 - 45s - loss: 0.0960 - accuracy: 0.9642 - val_loss: 0.1324 - val_accuracy: 0.9611 - 45s/epoch - 136ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0669 - accuracy: 0.9759 - val_loss: 0.1258 - val_accuracy: 0.9551 - 43s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0706 - accuracy: 0.9745 - val_loss: 0.1178 - val_accuracy: 0.9588 - 44s/epoch - 134ms/step
-<keras.callbacks.History object at 0x7fa19d8c21d0>
+<keras.callbacks.History object at 0x7f98dfaec790>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 43.584 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 56.774 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 ada76c6137..62a61c6b8c 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:53.951</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:12.258</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</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>04:43.584</p></td>
+<td><p>04:56.774</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:05.313</p></td>
+<td><p>01:07.774</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:53.005</p></td>
+<td><p>00:55.358</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:08.087</p></td>
+<td><p>00:08.260</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.960</p></td>
+<td><p>00:04.090</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></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 8ac181bcf3..30c93d3b43 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:44.835</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:47.134</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</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>00:32.987</p></td>
+<td><p>00:34.968</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>00:10.262</p></td>
+<td><p>00:10.520</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>00:01.579</p></td>
+<td><p>00:01.639</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 a520e17e8f..5ea307924a 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ 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 0x7fa19e08d050>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f98e0e81f80>
</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 57751808c6..e105806245 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:08.488</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.368</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.990</p></td>
+<td><p>00:05.703</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>00:01.116</p></td>
+<td><p>00:01.237</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>00:00.593</p></td>
+<td><p>00:00.609</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>00:00.571</p></td>
+<td><p>00:00.589</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>00:00.115</p></td>
+<td><p>00:00.121</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.051</p></td>
+<td><p>00:00.053</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.029</p></td>
+<td><p>00:00.031</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.024</p></td>
+<td><p>00:00.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 2bfa45621b..578bd38995 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpyi_arhl_/input0.cc'\nsource_filename = \"/tmp/tmpyi_arhl_/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/tmp04e4wlo9/input0.cc'\nsource_filename = \"/tmp/tmp04e4wlo9/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/objects.inv b/docs/objects.inv
index 822e36b6fe..1c95ebcaaa 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 62c50262a5..4570709658 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ 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>
@@ -1899,7 +1899,7 @@ 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/python/relay/backend.html b/docs/reference/api/python/relay/backend.html
index b44a062659..6a7a99e8ec 100644
--- a/docs/reference/api/python/relay/backend.html
+++ b/docs/reference/api/python/relay/backend.html
@@ -605,6 +605,26 @@ highest plevel.</p>
</dl>
</dd></dl>
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.relay.backend.te_compiler.lower_to_primfunc">
+<span class="sig-prename descclassname"><span class="pre">tvm.relay.backend.te_compiler.</span></span><span class="sig-name descname"><span class="pre">lower_to_primfunc</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">relay_func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.relay.backend.te_compiler.lower_to_primfunc" [...]
+<dd><p>Lower Relay Function to TIR PrimFunc.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>relay_func</strong> (<em>relay.Function</em>) – The source primitive function, created by FuseOps.</p></li>
+<li><p><strong>target</strong> (<a class="reference internal" href="../target.html#tvm.target.Target" title="tvm.target.Target"><em>Target</em></a>) – The compilation target.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>prim_func</strong> – The created prim func.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="../tir.html#tvm.tir.PrimFunc" title="tvm.tir.PrimFunc">tir.PrimFunc</a></p>
+</dd>
+</dl>
+</dd></dl>
+
<span class="target" id="module-tvm.relay.backend.graph_executor_codegen"></span><p>A compiler from a Relay expression to TVM’s graph executor.</p>
<p>The compiler is built from a few pieces.</p>
<p>First we define a compiler from a single Relay expression to the
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 7e1c2cf007..665edc8995 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/c547bbb13/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 2acf4a5396..4d728ef472 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/c547bbb13/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 b68b309d99..a4f57299c8 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/c547bbb13/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 4010f50a10..765e1b8557 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/c547bbb13/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 210c44b592..a2f950896d 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/c547bbb13/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 535e4e1867..b111e3959f 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/c547bbb13/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 e9361ce268..4859087178 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/c547bbb13/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 9775460237..089109f4cd 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/c547bbb13/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 b9a0966d14..d6b8c58e14 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/c547bbb13/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 e765636b75..3a13901b34 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/c547bbb13/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 ff4b68f10e..58fa9e51b5 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/c547bbb13/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 ded34ccef6..39edf3a1b6 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/c547bbb13/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 ccfab7af30..972e164158 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/c547bbb13/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 4cb8e371e2..4bc44ef0ff 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/c547bbb13/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 26060778db..64cf541db6 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/c547bbb13/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 adbbd25bc4..595b4b8764 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/c547bbb13/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 495e3eec2e..13d4d25757 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/c547bbb13/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 97d663bcfa..6fb91d8cab 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/c547bbb13/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 8c2e8e502f..088736bd02 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/c547bbb13/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 7d9eb509a3..f8d96da3c6 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/c547bbb13/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 5af2ef7df1..4d2225aee3 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/c547bbb13/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 d7a8497f72..9dce8f4c55 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/c547bbb13/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 b2067a82ee..8f63dc20dd 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/c547bbb13/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 b0a2827f64..31a8742ccb 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/c547bbb13/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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/c547bbb13/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/c6652bca8/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 7d9fea7566..b4c9890afc 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 89f294c52f..a6891d06c6 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:27.120</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:28.131</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +349,11 @@
</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>00:27.114</p></td>
+<td><p>00:28.125</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 63262afb78..fe1d13aaa0 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ 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 30.05s!
+resnet18_v1 inference graph built in 31.31s!
</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 4e3ca34af5..5b98d6b7fe 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 20.10s!
+yolov3-tiny inference graph built in 20.99s!
</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 0981b5498a..6dc4133b05 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>01:42.170</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:44.890</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</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>00:52.136</p></td>
+<td><p>00:53.455</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>00:50.034</p></td>
+<td><p>00:51.435</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 3040743f30..a8e6784ae5 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:03.220</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.235</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</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>00:02.747</p></td>
+<td><p>00:02.753</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>00:00.473</p></td>
+<td><p>00:00.482</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 c82dedbf42..03635376f1 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:00.841</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.848</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</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>00:00.447</p></td>
+<td><p>00:00.450</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>00:00.395</p></td>
+<td><p>00:00.399</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 c9dc1f36ef..9d6af8483a 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,9 +491,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><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">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -580,7 +577,7 @@ 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: 98.020 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.845 ms
</pre></div>
</div>
</div>
@@ -654,7 +651,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 28.480 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.399 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 7474ff6192..7610b6302f 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ 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: 2.19/2.19 result: MeasureResult(costs=(0.12236583720000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2158772945404053, timestamp=1670955369.5738146) [('tile_y', [-1, 8]), ('tile_x', [-1, 4])],None,23
-No: 2 GFLOPS: 1.61/2.19 result: MeasureResult(costs=(0.16625437599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8978428840637207, timestamp=1670955372.4807696) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
-No: 3 GFLOPS: 1.91/2.19 result: MeasureResult(costs=(0.14053541139999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.485870838165283, timestamp=1670955375.7764509) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
-No: 4 GFLOPS: 1.71/2.19 result: MeasureResult(costs=(0.1571701744,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7366943359375, timestamp=1670955379.314839) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
-No: 5 GFLOPS: 11.16/11.16 result: MeasureResult(costs=(0.0240434364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6191384792327881, timestamp=1670955380.8985522) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
-No: 6 GFLOPS: 12.18/12.18 result: MeasureResult(costs=(0.0220395392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.579561710357666, timestamp=1670955381.5079334) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
-No: 7 GFLOPS: 11.62/12.18 result: MeasureResult(costs=(0.0230923776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6502034664154053, timestamp=1670955382.137204) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
-No: 8 GFLOPS: 12.54/12.54 result: MeasureResult(costs=(0.021403288200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5823304653167725, timestamp=1670955382.7391253) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
-No: 9 GFLOPS: 2.03/12.54 result: MeasureResult(costs=(0.13206080979999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3163766860961914, timestamp=1670955385.1772897) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
-No: 10 GFLOPS: 3.27/12.54 result: MeasureResult(costs=(0.0821763226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5262548923492432, timestamp=1670955386.7436786) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
+No: 1 GFLOPS: 3.40/3.40 result: MeasureResult(costs=(0.0788423086,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5135166645050049, timestamp=1671006457.2592132) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
+No: 2 GFLOPS: 7.07/7.07 result: MeasureResult(costs=(0.037969686600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8380458354949951, timestamp=1671006458.122872) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+No: 3 GFLOPS: 12.84/12.84 result: MeasureResult(costs=(0.0209029732,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6002449989318848, timestamp=1671006459.540642) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+No: 4 GFLOPS: 0.51/12.84 result: MeasureResult(costs=(0.5294922854,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.716930866241455, timestamp=1671006469.1044455) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
+No: 5 GFLOPS: 1.72/12.84 result: MeasureResult(costs=(0.15631917339999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.726470708847046, timestamp=1671006472.8233833) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+No: 6 GFLOPS: 12.50/12.84 result: MeasureResult(costs=(0.021474067,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6199052333831787, timestamp=1671006473.429413) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+No: 7 GFLOPS: 10.40/12.84 result: MeasureResult(costs=(0.025814160600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.64272141456604, timestamp=1671006474.1021602) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+No: 8 GFLOPS: 12.73/12.84 result: MeasureResult(costs=(0.0210851084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6033406257629395, timestamp=1671006474.7040255) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
+No: 9 GFLOPS: 3.51/12.84 result: MeasureResult(costs=(0.07658358579999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4424622058868408, timestamp=1671006476.261223) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 10 GFLOPS: 1.61/12.84 result: MeasureResult(costs=(0.1668642154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.883350133895874, timestamp=1671006479.1867938) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
</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 7532c97669..a1d6cef1b4 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ 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': 520.0242369199975, 'median': 520.119645799997, 'std': 2.3306879659144153}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 525.7948484799978, 'median': 525.4736514499939, 'std': 2.3593836329757543}
</pre></div>
</div>
</div>
@@ -712,179 +712,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 13.49/ 17.57 GFLOPS | Progress: (4/20) | 11.37 s
-[Task 1/25] Current/Best: 7.64/ 18.57 GFLOPS | Progress: (8/20) | 15.12 s
-[Task 1/25] Current/Best: 15.32/ 18.57 GFLOPS | Progress: (12/20) | 19.88 s
-[Task 1/25] Current/Best: 22.58/ 22.58 GFLOPS | Progress: (16/20) | 22.63 s
-[Task 1/25] Current/Best: 12.33/ 22.58 GFLOPS | Progress: (20/20) | 26.40 s Done.
+[Task 1/25] Current/Best: 12.47/ 16.77 GFLOPS | Progress: (4/20) | 8.20 s
+[Task 1/25] Current/Best: 8.31/ 18.25 GFLOPS | Progress: (8/20) | 12.11 s
+[Task 1/25] Current/Best: 7.37/ 18.25 GFLOPS | Progress: (12/20) | 14.50 s
+[Task 1/25] Current/Best: 8.96/ 18.74 GFLOPS | Progress: (16/20) | 18.37 s
+[Task 1/25] Current/Best: 12.81/ 18.74 GFLOPS | Progress: (20/20) | 21.71 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.19/ 16.82 GFLOPS | Progress: (4/20) | 4.02 s
-[Task 2/25] Current/Best: 17.45/ 18.94 GFLOPS | Progress: (8/20) | 5.51 s
-[Task 2/25] Current/Best: 16.81/ 18.94 GFLOPS | Progress: (12/20) | 7.65 s
-[Task 2/25] Current/Best: 21.47/ 21.47 GFLOPS | Progress: (16/20) | 9.22 s
-[Task 2/25] Current/Best: 11.14/ 21.47 GFLOPS | Progress: (20/20) | 10.72 s Done.
+[Task 2/25] Current/Best: 15.45/ 15.45 GFLOPS | Progress: (4/20) | 4.26 s
+[Task 2/25] Current/Best: 12.95/ 18.13 GFLOPS | Progress: (8/20) | 5.86 s
+[Task 2/25] Current/Best: 13.46/ 18.13 GFLOPS | Progress: (12/20) | 7.68 s
+[Task 2/25] Current/Best: 3.73/ 18.13 GFLOPS | Progress: (16/20) | 10.92 s
+[Task 2/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (20/20) | 12.69 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 17.73/ 17.73 GFLOPS | Progress: (4/20) | 5.27 s
-[Task 3/25] Current/Best: 10.05/ 17.73 GFLOPS | Progress: (8/20) | 7.45 s
-[Task 3/25] Current/Best: 17.40/ 20.28 GFLOPS | Progress: (12/20) | 9.76 s
-[Task 3/25] Current/Best: 18.33/ 20.28 GFLOPS | Progress: (16/20) | 12.62 s
-[Task 3/25] Current/Best: 14.59/ 20.28 GFLOPS | Progress: (20/20) | 15.06 s Done.
+[Task 3/25] Current/Best: 9.69/ 19.91 GFLOPS | Progress: (4/20) | 4.66 s
+[Task 3/25] Current/Best: 14.55/ 19.91 GFLOPS | Progress: (8/20) | 7.48 s
+[Task 3/25] Current/Best: 16.54/ 19.91 GFLOPS | Progress: (12/20) | 10.64 s
+[Task 3/25] Current/Best: 10.66/ 19.91 GFLOPS | Progress: (16/20) | 14.69 s
+[Task 3/25] Current/Best: 10.39/ 19.91 GFLOPS | Progress: (20/20) | 17.51 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.28/ 15.64 GFLOPS | Progress: (4/20) | 6.24 s
-[Task 4/25] Current/Best: 10.70/ 15.64 GFLOPS | Progress: (8/20) | 10.87 s
-[Task 4/25] Current/Best: 15.17/ 16.37 GFLOPS | Progress: (12/20) | 13.18 s
-[Task 4/25] Current/Best: 14.45/ 16.37 GFLOPS | Progress: (16/20) | 15.34 s
-[Task 4/25] Current/Best: 11.91/ 17.71 GFLOPS | Progress: (20/20) | 18.19 s Done.
+[Task 4/25] Current/Best: 8.66/ 12.68 GFLOPS | Progress: (4/20) | 4.03 s
+[Task 4/25] Current/Best: 14.41/ 17.10 GFLOPS | Progress: (8/20) | 5.97 s
+[Task 4/25] Current/Best: 16.82/ 17.10 GFLOPS | Progress: (12/20) | 12.08 s
+[Task 4/25] Current/Best: 9.34/ 17.10 GFLOPS | Progress: (16/20) | 15.05 s
+[Task 4/25] Current/Best: 13.97/ 17.10 GFLOPS | Progress: (20/20) | 19.70 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 10.50/ 15.96 GFLOPS | Progress: (4/20) | 5.11 s
-[Task 5/25] Current/Best: 9.53/ 20.37 GFLOPS | Progress: (8/20) | 7.23 s
-[Task 5/25] Current/Best: 11.51/ 20.37 GFLOPS | Progress: (12/20) | 10.24 s
-[Task 5/25] Current/Best: 2.64/ 20.37 GFLOPS | Progress: (16/20) | 12.44 s
-[Task 5/25] Current/Best: 2.73/ 20.37 GFLOPS | Progress: (20/20) | 14.52 s Done.
+[Task 5/25] Current/Best: 10.60/ 14.72 GFLOPS | Progress: (4/20) | 4.26 s
+[Task 5/25] Current/Best: 12.88/ 15.73 GFLOPS | Progress: (8/20) | 6.67 s
+[Task 5/25] Current/Best: 11.66/ 15.73 GFLOPS | Progress: (12/20) | 8.62 s
+[Task 5/25] Current/Best: 18.12/ 18.35 GFLOPS | Progress: (16/20) | 11.18 s
+[Task 5/25] Current/Best: 5.77/ 18.35 GFLOPS | Progress: (20/20) | 13.15 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 14.67/ 19.76 GFLOPS | Progress: (4/20) | 3.99 s
-[Task 6/25] Current/Best: 21.39/ 21.39 GFLOPS | Progress: (8/20) | 6.54 s
-[Task 6/25] Current/Best: 8.91/ 21.39 GFLOPS | Progress: (12/20) | 9.18 s
-[Task 6/25] Current/Best: 9.13/ 21.39 GFLOPS | Progress: (16/20) | 11.45 s
-[Task 6/25] Current/Best: 9.67/ 21.39 GFLOPS | Progress: (20/20) | 18.40 s Done.
+[Task 6/25] Current/Best: 8.15/ 13.44 GFLOPS | Progress: (4/20) | 5.65 s
+[Task 6/25] Current/Best: 4.02/ 18.32 GFLOPS | Progress: (8/20) | 9.51 s
+[Task 6/25] Current/Best: 11.98/ 18.32 GFLOPS | Progress: (12/20) | 12.13 s
+[Task 6/25] Current/Best: 19.67/ 19.67 GFLOPS | Progress: (16/20) | 16.43 s
+[Task 6/25] Current/Best: 14.35/ 19.67 GFLOPS | Progress: (20/20) | 19.71 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 7.70/ 17.99 GFLOPS | Progress: (4/20) | 4.48 s
-[Task 7/25] Current/Best: 9.56/ 17.99 GFLOPS | Progress: (8/20) | 7.60 s
-[Task 7/25] Current/Best: 14.28/ 17.99 GFLOPS | Progress: (12/20) | 10.21 s
-[Task 7/25] Current/Best: 6.37/ 19.99 GFLOPS | Progress: (16/20) | 14.31 s
-[Task 7/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (20/20) | 16.62 s Done.
+[Task 7/25] Current/Best: 7.68/ 21.00 GFLOPS | Progress: (4/20) | 5.24 s
+[Task 7/25] Current/Best: 3.09/ 21.00 GFLOPS | Progress: (8/20) | 9.59 s
+[Task 7/25] Current/Best: 3.12/ 21.00 GFLOPS | Progress: (12/20) | 12.62 s
+[Task 7/25] Current/Best: 15.80/ 21.00 GFLOPS | Progress: (16/20) | 15.66 s
+[Task 7/25] Current/Best: 15.51/ 21.00 GFLOPS | Progress: (20/20) | 17.93 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 12.58/ 12.62 GFLOPS | Progress: (4/20) | 9.06 s
-[Task 8/25] Current/Best: 2.62/ 14.15 GFLOPS | Progress: (8/20) | 21.18 s
-[Task 8/25] Current/Best: 15.38/ 15.72 GFLOPS | Progress: (12/20) | 23.47 s
-[Task 8/25] Current/Best: 4.50/ 15.72 GFLOPS | Progress: (16/20) | 25.99 s
-[Task 8/25] Current/Best: 11.79/ 15.72 GFLOPS | Progress: (20/20) | 29.97 s Done.
+[Task 8/25] Current/Best: 12.59/ 12.59 GFLOPS | Progress: (4/20) | 10.86 s
+[Task 8/25] Current/Best: 15.86/ 15.86 GFLOPS | Progress: (8/20) | 20.37 s
+[Task 8/25] Current/Best: 2.88/ 15.86 GFLOPS | Progress: (12/20) | 30.72 s
+[Task 8/25] Current/Best: 12.10/ 15.86 GFLOPS | Progress: (16/20) | 34.03 s
+[Task 8/25] Current/Best: 2.78/ 17.46 GFLOPS | Progress: (20/20) | 40.51 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 12.23/ 12.23 GFLOPS | Progress: (4/20) | 12.64 s
-[Task 9/25] Current/Best: 8.30/ 13.79 GFLOPS | Progress: (8/20) | 15.55 s
-[Task 9/25] Current/Best: 7.32/ 15.61 GFLOPS | Progress: (12/20) | 17.88 s
-[Task 9/25] Current/Best: 16.09/ 21.61 GFLOPS | Progress: (16/20) | 19.35 s
-[Task 9/25] Current/Best: 20.88/ 21.61 GFLOPS | Progress: (20/20) | 21.44 s
+[Task 9/25] Current/Best: 13.33/ 13.33 GFLOPS | Progress: (4/20) | 13.01 s
+[Task 9/25] Current/Best: 6.63/ 13.33 GFLOPS | Progress: (8/20) | 17.54 s
+[Task 9/25] Current/Best: 5.18/ 15.56 GFLOPS | Progress: (12/20) | 23.36 s
+[Task 9/25] Current/Best: 5.86/ 20.36 GFLOPS | Progress: (16/20) | 24.95 s
+[Task 9/25] Current/Best: 10.54/ 20.36 GFLOPS | Progress: (20/20) | 28.67 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 12.80/ 15.97 GFLOPS | Progress: (4/20) | 3.89 s
-[Task 10/25] Current/Best: 10.03/ 15.97 GFLOPS | Progress: (8/20) | 6.42 s
-[Task 10/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (12/20) | 8.35 s
-[Task 10/25] Current/Best: 9.55/ 16.95 GFLOPS | Progress: (16/20) | 10.68 s
-[Task 10/25] Current/Best: 13.63/ 16.95 GFLOPS | Progress: (20/20) | 12.84 s Done.
+[Task 10/25] Current/Best: 3.02/ 19.69 GFLOPS | Progress: (4/20) | 3.87 s
+[Task 10/25] Current/Best: 13.05/ 19.69 GFLOPS | Progress: (8/20) | 5.74 s
+[Task 10/25] Current/Best: 5.63/ 19.69 GFLOPS | Progress: (12/20) | 7.65 s
+[Task 10/25] Current/Best: 4.83/ 19.69 GFLOPS | Progress: (16/20) | 10.68 s
+[Task 10/25] Current/Best: 12.87/ 19.69 GFLOPS | Progress: (20/20) | 12.42 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 16.25/ 20.16 GFLOPS | Progress: (4/20) | 5.85 s
-[Task 11/25] Current/Best: 4.56/ 20.16 GFLOPS | Progress: (8/20) | 8.36 s
-[Task 11/25] Current/Best: 13.05/ 20.16 GFLOPS | Progress: (12/20) | 11.28 s
-[Task 11/25] Current/Best: 15.88/ 20.16 GFLOPS | Progress: (16/20) | 14.29 s
-[Task 11/25] Current/Best: 15.02/ 20.16 GFLOPS | Progress: (20/20) | 16.92 s Done.
+[Task 11/25] Current/Best: 17.25/ 19.30 GFLOPS | Progress: (4/20) | 4.92 s
+[Task 11/25] Current/Best: 7.98/ 19.30 GFLOPS | Progress: (8/20) | 7.42 s
+[Task 11/25] Current/Best: 17.44/ 19.30 GFLOPS | Progress: (12/20) | 10.60 s
+[Task 11/25] Current/Best: 23.48/ 23.48 GFLOPS | Progress: (16/20) | 13.16 s
+[Task 11/25] Current/Best: 12.63/ 23.48 GFLOPS | Progress: (20/20) | 15.94 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 3.62/ 18.71 GFLOPS | Progress: (4/20) | 4.26 s
-[Task 12/25] Current/Best: 13.29/ 20.64 GFLOPS | Progress: (8/20) | 7.14 s
-[Task 12/25] Current/Best: 15.62/ 20.64 GFLOPS | Progress: (12/20) | 9.00 s
-[Task 12/25] Current/Best: 3.01/ 20.64 GFLOPS | Progress: (16/20) | 11.87 s
-[Task 12/25] Current/Best: 12.39/ 20.64 GFLOPS | Progress: (20/20) | 15.54 s Done.
+[Task 12/25] Current/Best: 15.44/ 18.33 GFLOPS | Progress: (4/20) | 4.45 s
+[Task 12/25] Current/Best: 17.75/ 18.33 GFLOPS | Progress: (8/20) | 11.16 s
+[Task 12/25] Current/Best: 4.26/ 18.33 GFLOPS | Progress: (12/20) | 13.93 s
+[Task 12/25] Current/Best: 16.20/ 18.33 GFLOPS | Progress: (16/20) | 16.42 s
+[Task 12/25] Current/Best: 5.68/ 18.33 GFLOPS | Progress: (20/20) | 20.04 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 23.30/ 23.30 GFLOPS | Progress: (4/20) | 5.05 s
-[Task 13/25] Current/Best: 11.47/ 23.30 GFLOPS | Progress: (8/20) | 10.55 s
-[Task 13/25] Current/Best: 19.85/ 23.30 GFLOPS | Progress: (12/20) | 14.41 s
-[Task 13/25] Current/Best: 19.13/ 23.30 GFLOPS | Progress: (16/20) | 17.53 s
-[Task 13/25] Current/Best: 8.70/ 23.30 GFLOPS | Progress: (20/20) | 20.36 s Done.
+[Task 13/25] Current/Best: 17.17/ 18.26 GFLOPS | Progress: (4/20) | 4.33 s
+[Task 13/25] Current/Best: 18.12/ 18.26 GFLOPS | Progress: (8/20) | 9.18 s
+[Task 13/25] Current/Best: 17.73/ 18.26 GFLOPS | Progress: (12/20) | 11.36 s
+[Task 13/25] Current/Best: 11.56/ 18.26 GFLOPS | Progress: (16/20) | 14.87 s
+[Task 13/25] Current/Best: 13.46/ 19.35 GFLOPS | Progress: (20/20) | 17.48 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 10.99/ 16.30 GFLOPS | Progress: (4/20) | 5.02 s
-[Task 14/25] Current/Best: 21.25/ 21.25 GFLOPS | Progress: (8/20) | 7.57 s
-[Task 14/25] Current/Best: 18.62/ 21.25 GFLOPS | Progress: (12/20) | 10.58 s
-[Task 14/25] Current/Best: 10.11/ 21.25 GFLOPS | Progress: (16/20) | 14.50 s
-[Task 14/25] Current/Best: 9.45/ 21.25 GFLOPS | Progress: (20/20) | 18.67 s Done.
+[Task 14/25] Current/Best: 9.02/ 20.25 GFLOPS | Progress: (4/20) | 5.71 s
+[Task 14/25] Current/Best: 8.71/ 20.25 GFLOPS | Progress: (8/20) | 10.35 s
+[Task 14/25] Current/Best: 9.85/ 20.25 GFLOPS | Progress: (12/20) | 16.73 s
+[Task 14/25] Current/Best: 13.24/ 20.25 GFLOPS | Progress: (16/20) | 19.40 s
+[Task 14/25] Current/Best: 12.53/ 20.25 GFLOPS | Progress: (20/20) | 22.54 s Done.
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 13.58/ 19.13 GFLOPS | Progress: (4/20) | 3.81 s
-[Task 15/25] Current/Best: 12.03/ 19.13 GFLOPS | Progress: (8/20) | 7.54 s
-[Task 15/25] Current/Best: 16.21/ 22.37 GFLOPS | Progress: (12/20) | 12.00 s
-[Task 15/25] Current/Best: 15.19/ 22.37 GFLOPS | Progress: (16/20) | 14.16 s
-[Task 15/25] Current/Best: 17.28/ 22.37 GFLOPS | Progress: (20/20) | 16.52 s
-[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 11.08/ 19.66 GFLOPS | Progress: (4/20) | 4.96 s Done.
- Done.
+[Task 15/25] Current/Best: 15.94/ 15.94 GFLOPS | Progress: (4/20) | 4.77 s
+[Task 15/25] Current/Best: 3.09/ 15.94 GFLOPS | Progress: (8/20) | 8.80 s
+[Task 15/25] Current/Best: 1.70/ 17.04 GFLOPS | Progress: (12/20) | 11.97 s Done.
-[Task 16/25] Current/Best: 8.00/ 19.66 GFLOPS | Progress: (8/20) | 6.82 s
-[Task 16/25] Current/Best: 11.55/ 19.66 GFLOPS | Progress: (12/20) | 9.18 s
-[Task 16/25] Current/Best: 11.42/ 19.66 GFLOPS | Progress: (16/20) | 12.48 s
-[Task 16/25] Current/Best: 5.98/ 19.66 GFLOPS | Progress: (20/20) | 15.66 s Done.
+[Task 15/25] Current/Best: 6.87/ 17.04 GFLOPS | Progress: (16/20) | 14.16 s
+[Task 15/25] Current/Best: 15.75/ 17.04 GFLOPS | Progress: (20/20) | 15.91 s Done.
+
+[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 16/25] Current/Best: 14.07/ 14.63 GFLOPS | Progress: (4/20) | 4.15 s
+[Task 16/25] Current/Best: 7.95/ 17.62 GFLOPS | Progress: (8/20) | 5.83 s
+[Task 16/25] Current/Best: 9.87/ 17.62 GFLOPS | Progress: (12/20) | 8.23 s
+[Task 16/25] Current/Best: 7.03/ 17.62 GFLOPS | Progress: (16/20) | 13.06 s
+[Task 16/25] Current/Best: 11.96/ 17.62 GFLOPS | Progress: (20/20) | 15.23 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 8.82/ 16.54 GFLOPS | Progress: (4/20) | 4.12 s
-[Task 17/25] Current/Best: 22.02/ 22.02 GFLOPS | Progress: (8/20) | 6.19 s
-[Task 17/25] Current/Best: 5.34/ 22.02 GFLOPS | Progress: (12/20) | 8.85 s
-[Task 17/25] Current/Best: 9.40/ 22.02 GFLOPS | Progress: (16/20) | 12.56 s
-[Task 17/25] Current/Best: 22.98/ 22.98 GFLOPS | Progress: (20/20) | 15.80 s Done.
+[Task 17/25] Current/Best: 16.38/ 20.28 GFLOPS | Progress: (4/20) | 6.29 s
+[Task 17/25] Current/Best: 16.17/ 20.28 GFLOPS | Progress: (8/20) | 8.48 s
+[Task 17/25] Current/Best: 7.75/ 21.02 GFLOPS | Progress: (12/20) | 10.88 s
+[Task 17/25] Current/Best: 20.39/ 21.02 GFLOPS | Progress: (16/20) | 13.25 s
+[Task 17/25] Current/Best: 10.71/ 21.02 GFLOPS | Progress: (20/20) | 15.99 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 17.04/ 21.16 GFLOPS | Progress: (4/20) | 3.53 s
-[Task 18/25] Current/Best: 5.87/ 23.43 GFLOPS | Progress: (8/20) | 5.90 s
-[Task 18/25] Current/Best: 18.79/ 23.43 GFLOPS | Progress: (12/20) | 7.70 s
-[Task 18/25] Current/Best: 19.55/ 23.43 GFLOPS | Progress: (16/20) | 10.52 s
-[Task 18/25] Current/Best: 9.04/ 23.43 GFLOPS | Progress: (20/20) | 16.13 s Done.
+[Task 18/25] Current/Best: 3.10/ 16.55 GFLOPS | Progress: (4/20) | 4.63 s
+[Task 18/25] Current/Best: 17.36/ 17.36 GFLOPS | Progress: (8/20) | 8.34 s
+[Task 18/25] Current/Best: 15.08/ 17.36 GFLOPS | Progress: (12/20) | 11.66 s
+[Task 18/25] Current/Best: 10.04/ 21.82 GFLOPS | Progress: (16/20) | 17.43 s
+[Task 18/25] Current/Best: 16.39/ 21.82 GFLOPS | Progress: (20/20) | 19.66 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (4/20) | 5.46 s
-[Task 19/25] Current/Best: 12.20/ 19.72 GFLOPS | Progress: (8/20) | 10.79 s
-[Task 19/25] Current/Best: 17.24/ 19.72 GFLOPS | Progress: (12/20) | 13.69 s
-[Task 19/25] Current/Best: 8.27/ 19.72 GFLOPS | Progress: (16/20) | 17.92 s
-[Task 19/25] Current/Best: 12.15/ 19.90 GFLOPS | Progress: (20/20) | 21.84 s Done.
+[Task 19/25] Current/Best: 11.48/ 19.41 GFLOPS | Progress: (4/20) | 4.26 s
+[Task 19/25] Current/Best: 21.11/ 23.07 GFLOPS | Progress: (8/20) | 7.79 s
+[Task 19/25] Current/Best: 11.35/ 23.07 GFLOPS | Progress: (12/20) | 12.03 s
+[Task 19/25] Current/Best: 18.36/ 23.07 GFLOPS | Progress: (16/20) | 14.37 s
+[Task 19/25] Current/Best: 19.54/ 23.07 GFLOPS | Progress: (20/20) | 18.97 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 2.29/ 12.71 GFLOPS | Progress: (4/20) | 6.15 s
-[Task 20/25] Current/Best: 10.47/ 12.71 GFLOPS | Progress: (8/20) | 8.17 s
-[Task 20/25] Current/Best: 8.12/ 14.29 GFLOPS | Progress: (12/20) | 11.75 s
-[Task 20/25] Current/Best: 8.61/ 14.29 GFLOPS | Progress: (16/20) | 15.12 s
-[Task 20/25] Current/Best: 14.66/ 17.44 GFLOPS | Progress: (20/20) | 17.01 s
+[Task 20/25] Current/Best: 11.85/ 17.46 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 20/25] Current/Best: 10.58/ 17.46 GFLOPS | Progress: (8/20) | 6.65 s
+[Task 20/25] Current/Best: 13.64/ 17.46 GFLOPS | Progress: (12/20) | 10.02 s
+[Task 20/25] Current/Best: 4.61/ 17.46 GFLOPS | Progress: (16/20) | 13.17 s
+[Task 20/25] Current/Best: 19.33/ 19.33 GFLOPS | Progress: (20/20) | 15.43 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 10.32/ 18.75 GFLOPS | Progress: (4/20) | 4.74 s
-[Task 21/25] Current/Best: 4.33/ 18.75 GFLOPS | Progress: (8/20) | 6.37 s
-[Task 21/25] Current/Best: 6.48/ 21.20 GFLOPS | Progress: (12/20) | 8.84 s
-[Task 21/25] Current/Best: 19.36/ 21.20 GFLOPS | Progress: (16/20) | 11.02 s
-[Task 21/25] Current/Best: 13.71/ 21.20 GFLOPS | Progress: (20/20) | 12.94 s
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 15.90/ 15.90 GFLOPS | Progress: (4/20) | 6.93 s
-[Task 22/25] Current/Best: 9.61/ 15.90 GFLOPS | Progress: (8/20) | 8.77 s
-[Task 22/25] Current/Best: 10.92/ 17.68 GFLOPS | Progress: (12/20) | 10.42 s
-[Task 22/25] Current/Best: 8.08/ 19.69 GFLOPS | Progress: (16/20) | 12.32 s
-[Task 22/25] Current/Best: 8.14/ 19.69 GFLOPS | Progress: (20/20) | 15.17 s Done.
+[Task 21/25] Current/Best: 11.82/ 11.82 GFLOPS | Progress: (4/20) | 5.58 s
+[Task 21/25] Current/Best: 2.46/ 15.13 GFLOPS | Progress: (8/20) | 7.64 s
+[Task 21/25] Current/Best: 16.02/ 16.02 GFLOPS | Progress: (12/20) | 10.01 s
+[Task 21/25] Current/Best: 15.99/ 18.44 GFLOPS | Progress: (16/20) | 12.43 s
+[Task 21/25] Current/Best: 3.12/ 18.44 GFLOPS | Progress: (20/20) | 15.14 s
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
+[Task 22/25] Current/Best: 16.67/ 17.80 GFLOPS | Progress: (4/20) | 4.48 s
+[Task 22/25] Current/Best: 4.62/ 17.80 GFLOPS | Progress: (8/20) | 6.46 s
+[Task 22/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (12/20) | 8.50 s
+[Task 22/25] Current/Best: 14.44/ 18.50 GFLOPS | Progress: (16/20) | 11.43 s
+[Task 22/25] Current/Best: 8.56/ 18.50 GFLOPS | Progress: (20/20) | 13.84 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 9.96/ 11.95 GFLOPS | Progress: (4/20) | 6.79 s
-[Task 23/25] Current/Best: 11.94/ 17.85 GFLOPS | Progress: (8/20) | 10.36 s
-[Task 23/25] Current/Best: 14.30/ 18.59 GFLOPS | Progress: (12/20) | 13.34 s
-[Task 23/25] Current/Best: 13.68/ 18.59 GFLOPS | Progress: (16/20) | 17.42 s
-[Task 23/25] Current/Best: 18.16/ 18.59 GFLOPS | Progress: (20/20) | 20.61 s Done.
+[Task 23/25] Current/Best: 13.96/ 23.07 GFLOPS | Progress: (4/20) | 4.68 s
+[Task 23/25] Current/Best: 13.83/ 23.07 GFLOPS | Progress: (8/20) | 6.99 s
+[Task 23/25] Current/Best: 9.12/ 23.07 GFLOPS | Progress: (12/20) | 9.64 s
+[Task 23/25] Current/Best: 11.79/ 23.07 GFLOPS | Progress: (16/20) | 12.59 s
+[Task 23/25] Current/Best: 20.54/ 23.07 GFLOPS | Progress: (20/20) | 18.35 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 4.03/ 4.03 GFLOPS | Progress: (4/20) | 12.84 s Done.
- Done.
-
-[Task 24/25] Current/Best: 5.64/ 6.33 GFLOPS | Progress: (8/20) | 19.04 s
-[Task 24/25] Current/Best: 8.85/ 8.85 GFLOPS | Progress: (12/20) | 23.52 s
-[Task 24/25] Current/Best: 6.96/ 8.85 GFLOPS | Progress: (16/20) | 33.88 s
-[Task 24/25] Current/Best: 1.44/ 8.85 GFLOPS | Progress: (20/20) | 44.95 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 9.06/ 9.06 GFLOPS | Progress: (4/20) | 6.87 s
-[Task 25/25] Current/Best: 5.75/ 9.06 GFLOPS | Progress: (8/20) | 17.80 s
-[Task 25/25] Current/Best: 3.96/ 9.06 GFLOPS | Progress: (12/20) | 29.64 s Done.
-
-[Task 25/25] Current/Best: 2.89/ 9.06 GFLOPS | Progress: (16/20) | 41.42 s
-[Task 25/25] Current/Best: 5.16/ 9.06 GFLOPS | Progress: (20/20) | 43.55 s
+[Task 24/25] Current/Best: 7.66/ 7.66 GFLOPS | Progress: (4/20) | 12.61 s
+[Task 24/25] Current/Best: 2.44/ 7.66 GFLOPS | Progress: (8/20) | 23.61 s
+[Task 24/25] Current/Best: 5.49/ 7.66 GFLOPS | Progress: (12/20) | 35.18 s
+[Task 24/25] Current/Best: 7.96/ 7.96 GFLOPS | Progress: (16/20) | 40.12 s
+[Task 24/25] Current/Best: 2.79/ 9.59 GFLOPS | Progress: (20/20) | 48.29 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 25/25] Current/Best: 3.52/ 8.17 GFLOPS | Progress: (4/20) | 4.58 s
+[Task 25/25] Current/Best: 2.99/ 8.17 GFLOPS | Progress: (8/20) | 6.00 s
+[Task 25/25] Current/Best: 3.31/ 8.17 GFLOPS | Progress: (12/20) | 8.63 s
+[Task 25/25] Current/Best: 1.52/ 8.17 GFLOPS | Progress: (16/20) | 10.32 s
+[Task 25/25] Current/Best: 7.94/ 8.17 GFLOPS | Progress: (20/20) | 21.28 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -983,8 +983,8 @@ 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': 425.32732617999727, 'median': 425.49077234999686, 'std': 2.3648607733454887}
-unoptimized: {'mean': 520.0242369199975, 'median': 520.119645799997, 'std': 2.3306879659144153}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 443.2241799900021, 'median': 442.8553297999997, 'std': 1.2358620085024732}
+unoptimized: {'mean': 525.7948484799978, 'median': 525.4736514499939, 'std': 2.3593836329757543}
</pre></div>
</div>
</div>
@@ -998,7 +998,7 @@ 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> ( 11 minutes 48.924 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 59.482 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 bbd93293d4..18ae7055de 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ 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>2.054e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.285e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 6325f70ee6..1965c68381 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ 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, 0x21b372b0)), stage(b, placeholder(b, 0x1a82a290)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xd9615d0)), stage(b, placeholder(b, 0xeb9fdd0)), 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=[it [...]
</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 1a7de908f2..3d036a9a59 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>15:17.700</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:34.667</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,54 +349,54 @@
</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>11:48.924</p></td>
+<td><p>11:59.482</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>01:28.480</p></td>
+<td><p>01:26.399</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:59.927</p></td>
+<td><p>01:02.489</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>00:34.164</p></td>
+<td><p>00:35.672</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>00:23.655</p></td>
+<td><p>00:28.023</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.535</p></td>
+<td><p>00:01.555</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.833</p></td>
+<td><p>00:00.844</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>00:00.171</p></td>
+<td><p>00:00.191</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>00:00.006</p></td>
+<td><p>00:00.007</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>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_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>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="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>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index f14a501494..69eea63f0f 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -551,8 +551,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+naive: 0.000008
</pre></div>
</div>
</div>
@@ -600,7 +600,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
</pre></div>
</div>
</div>
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.184270000379911e-06 1.0
- naive 6.6858000000000004e-06 0.930616471770472
-parallel 6.9414999999999995e-06 0.96620811851906
- vector 2.4681399999999997e-05 3.4354777867055137
+ numpy 7.699140001022897e-06 1.0
+ naive 7.8285e-06 1.0168018764381368
+parallel 7.745299999999999e-06 1.0059954746856101
+ vector 2.45903e-05 3.193902175662862
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ 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: 0.018643
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019289
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.304013
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.442906
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.305587
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.330149
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.348980
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.352015
@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, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.119618
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.143185
@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, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109821
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109962
@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, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110859
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.113218
@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, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.149532
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.148249
@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, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ 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 3.3040130473 1.0
- blocking 0.3055870649 0.09248966651318828
- vectorization 0.3489801616 0.10562311849379119
-loop permutation 0.11961816480000001 0.03620390206925803
- array packing 0.10982061369999999 0.03323855327682319
- block caching 0.1108594217 0.03355296123621334
- parallelization 0.1495322029 0.04525775193962867
+ none 3.4429063483 1.0
+ blocking 0.3301487045 0.0958924440866703
+ vectorization 0.3520149301 0.10224353917550329
+loop permutation 0.1431853593 0.04158851412577646
+ array packing 0.10996156940000001 0.03193858858644111
+ block caching 0.11321799670000002 0.0328844253216192
+ parallelization 0.1482489117 0.04305923446718227
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1520,6 +1520,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.489 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>