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 2022/11/15 13:08:36 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@034dc67d032aac3b848e15a87a7fbb5b72a0b909)
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 5460ec7a21 deploying docs (apache/tvm@034dc67d032aac3b848e15a87a7fbb5b72a0b909)
5460ec7a21 is described below
commit 5460ec7a21dff9dd49fb54aeb03de6ae18e51746
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Nov 15 13:08:29 2022 +0000
deploying docs (apache/tvm@034dc67d032aac3b848e15a87a7fbb5b72a0b909)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 314727 -> 324292 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23008 -> 23851 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_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 | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1686 +++++++-------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 71 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 224 +--
.../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 | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../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 | 60 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_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 | 13 +-
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_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 54 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1686 +++++++-------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 71 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 224 +--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
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 | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../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 | 276 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
127 files changed, 2062 insertions(+), 3530 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 44d42e7073..fd04aec899 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 979e8de9bd..176d23232e 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 c0d09476c8..792db4e0af 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 22.704 seconds)
+ **Total running time of the script:** ( 1 minutes 11.345 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 74b731c412..39abcd3099 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 970ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 942ms/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 e002c83f37..13c87f8fb6 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.zipf3c04b29-7dab-4be3-aa9e-a75f69ae701c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip15cabb9c-945d-461e-a62b-cdb0c4474b5d 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 120d69a576..c046c9936f 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, 57.0MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 68.0MB/s]
55%|#####4 | 22.6M/41.5M [00:00<00:00, 67.0MB/s]
70%|####### | 29.1M/41.5M [00:00<00:00, 60.6MB/s]
84%|########4 | 35.0M/41.5M [00:00<00:00, 52.0MB/s]
98%|#########8| 40.8M/41.5M [00:00<00:00, 54.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 58.1MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 71.2MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 61.7MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 63.4MB/s]
69%|######8 | 28.5M/41.5M [00:00<00:00, 57.6MB/s]
82%|########2 | 34.0M/41.5M [00:00<00:00, 47.8MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 57.5MB/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 24c018d269..e71be8feab 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]
18%|#7 | 7.99M/44.7M [00:00<00:00, 46.9MB/s]
32%|###2 | 14.3M/44.7M [00:00<00:00, 46.4MB/s]
42%|####1 | 18.7M/44.7M [00:00<00:00, 44.9MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 40.6MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 44.0MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 50.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 49.8MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 78.3MB/s]
40%|###9 | 17.7M/44.7M [00:00<00:00, 91.5MB/s]
59%|#####9 | 26.4M/44.7M [00:00<00:00, 55.8MB/s]
74%|#######3 | 32.8M/44.7M [00:00<00:00, 50.3MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 52.2MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 58.0MB/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 889ff76c72..68c2fe71d7 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 11.496 seconds)
+ **Total running time of the script:** ( 1 minutes 10.066 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 90fb3e40a4..459744644e 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**06:01.124** total execution time for **how_to_compile_models** files:
+**05:41.107** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:22.704 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.345 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.496 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.066 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.587 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:44.957 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.946 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.583 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.628 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.915 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.945 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.073 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.966 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.317 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.625 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.517 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.182 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.440 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.395 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index d62d02d0ae..040cc1fc4c 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
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2278 16.2067 16.4092 16.0635 0.1238
+ 15.5598 15.5219 15.8895 15.4592 0.1152
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 30e802437f..6741b97b17 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, 75.1MB/s]
9%|8 | 15.2M/170M [00:00<00:02, 74.2MB/s]
13%|#3 | 22.2M/170M [00:00<00:02, 62.2MB/s]
17%|#6 | 28.3M/170M [00:00<00:02, 57.6MB/s]
20%|#9 | 33.9M/170M [00:00<00:02, 52.6MB/s]
24%|##3 | 40.4M/170M [00:00<00:02, 57.0MB/s]
28%|##7 | 47.2M/170M [00:00<00:02, 61.1MB/s]
31%|###1 | 53.1M/170M [00:00<00:02, 51.4MB/s]
36%|###6 | 61.4M/170M [00:01<00:01, 60.5MB/s]
40%|###9 | 67.6M/170M [00:01<00:02, 52.9MB/s]
43%|####2 | 73.0M/170M [00:01<00:01, 51.7MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 51.1MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 45.9MB/s]
56%|#####5 | 94.3M/170M [00:01<00:01, 47.5MB/s]
59%|#####8 | 100M/170M [00:01<00:01, 50.1MB/s]
63%|######3 | 108M/170M [00:02<00:01, 57.2MB/s]
67%|######6 | 113M/170M [00:02<00:01, 51.6MB/s]
71%|####### | 120M/170M [00:02<00:00, 54.8MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 60.1MB/s]
80%|######## | 136M/170M [00:02<00:00, 57.0MB/s]
85%|########4 | 144M/170M [00:02<00:00, 63.3MB/s]
89%|########9 | 152M/170M [00:02<00:00, 60.2MB/s]
94%|#########4| 160M/170M [00:03<00:00, 55.4MB/s]
99%|#########8| 168M/170M [00:03<00:00, 57.8MB/s]
100%|##########| 170M/170M [00:03<00:00, 56.3MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:02, 60.3MB/s]
7%|7 | 12.1M/170M [00:00<00:03, 49.6MB/s]
10%|9 | 16.9M/170M [00:00<00:03, 47.6MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 50.5MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 57.4MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 59.7MB/s]
27%|##7 | 46.3M/170M [00:00<00:02, 59.8MB/s]
31%|### | 52.0M/170M [00:00<00:02, 56.7MB/s]
36%|###5 | 60.3M/170M [00:01<00:01, 65.0MB/s]
39%|###9 | 66.7M/170M [00:01<00:01, 63.5MB/s]
43%|####2 | 72.8M/170M [00:01<00:01, 63.6MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 65.5MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 59.0MB/s]
54%|#####4 | 92.1M/170M [00:01<00:01, 51.4MB/s]
57%|#####7 | 97.2M/170M [00:01<00:01, 49.3MB/s]
61%|######1 | 104M/170M [00:01<00:01, 48.2MB/s]
66%|######5 | 112M/170M [00:02<00:01, 55.2MB/s
]
71%|####### | 120M/170M [00:02<00:00, 55.2MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 53.5MB/s]
80%|######## | 136M/170M [00:02<00:00, 55.9MB/s]
85%|########4 | 144M/170M [00:02<00:00, 53.5MB/s]
88%|########8 | 150M/170M [00:02<00:00, 50.9MB/s]
91%|#########1| 155M/170M [00:02<00:00, 47.5MB/s]
94%|#########4| 160M/170M [00:03<00:00, 41.3MB/s]
96%|#########6| 164M/170M [00:03<00:00, 38.2MB/s]
99%|#########8| 168M/170M [00:03<00:00, 36.6MB/s]
100%|##########| 170M/170M [00:03<00:00, 51.8MB/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 13.965 seconds)
+ **Total running time of the script:** ( 3 minutes 8.345 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 f199f08196..e3d84c67f0 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]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 58.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 74.0MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
75%|#######5 | 10.2M/13.6M [00:00<00:00, 107MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 127MB/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)
- 88.9665 88.8580 94.4067 88.7508 0.5745
+ 90.1390 90.0956 91.8675 89.9643 0.2382
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.160 seconds)
+ **Total running time of the script:** ( 1 minutes 4.408 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 026c96ba25..76b6b5a1a9 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)
- 118.7686 118.7043 119.7815 118.0459 0.3485
+ 117.5577 117.1141 120.8395 115.9301 1.1803
@@ -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 25.879 seconds)
+ **Total running time of the script:** ( 2 minutes 21.058 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 269e6047f6..cff8e27114 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 35.353 seconds)
+ **Total running time of the script:** ( 1 minutes 34.639 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 697058d38b..80c0a44ebb 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%|4 | 6171/132723 [00:00<00:02, 61701.09KB/s]
11%|#1 | 14843/132723 [00:00<00:01, 76410.30KB/s]
18%|#7 | 23515/132723 [00:00<00:01, 81114.04KB/s]
24%|##4 | 32142/132723 [00:00<00:01, 83145.91KB/s]
31%|### | 40831/132723 [00:00<00:01, 84492.43KB/s]
37%|###7 | 49396/132723 [00:00<00:01, 82871.36KB/s]
43%|####3 | 57691/132723 [00:00<00:01, 73223.98KB/s]
49%|####9 | 65197/132723 [00:00<00:00, 70633.56KB/s]
55%|#####4 | 72386/132723 [00:00<00:00, 66933.18KB/s]
60%|###### | 79980/132723 [00:01<00:00, 69418.53KB/s]
66%|######5 | 87020/132723 [00:01<00:00, 63332.39KB/s]
72%|#######1 | 95348/132723 [00:01<00:00, 68684.41KB/s]
78%|#######8 | 103819/132723 [00:01<00:00, 73125.44KB/s]
85%|########4 | 112394/132723 [00:01<00:00, 76705.70KB/s]
91%|#########1| 120976/132723 [00:01<00:00, 79332.85KB/s]
98%|########
#7| 129574/132723 [00:01<00:00, 81269.80KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75466.07KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5510/132723 [00:00<00:02, 55095.72KB/s]
11%|# | 14232/132723 [00:00<00:01, 73977.89KB/s]
16%|#6 | 21865/132723 [00:00<00:01, 75046.43KB/s]
23%|##3 | 30549/132723 [00:00<00:01, 79697.24KB/s]
29%|##9 | 39045/132723 [00:00<00:01, 81592.25KB/s]
36%|###5 | 47677/132723 [00:00<00:01, 83195.45KB/s]
42%|####2 | 56298/132723 [00:00<00:00, 84178.42KB/s]
49%|####8 | 64996/132723 [00:00<00:00, 85069.03KB/s]
56%|#####5 | 73711/132723 [00:00<00:00, 85718.15KB/s]
62%|######2 | 82429/132723 [00:01<00:00, 86165.77KB/s]
69%|######8 | 91116/132723 [00:01<00:00, 86379.11KB/s]
75%|#######5 | 99838/132723 [00:01<00:00, 86631.72KB/s]
82%|########1 | 108510/132723 [00:01<00:00, 86656.67KB/s]
88%|########8 | 117176/132723 [00:01<00:00, 86574.79KB/s]
95%|#########4| 125902/132723 [00:01<00:00, 86773.86KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83993.06KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 0.177 seconds)
+ **Total running time of the script:** ( 2 minutes 56.170 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 41e2d8f309..2404805079 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:47.465** total execution time for **how_to_deploy_models** files:
+**12:28.240** 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``) | 03:13.965 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:08.345 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:00.177 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:56.170 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:25.879 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:21.058 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:35.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:34.639 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.160 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:04.408 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.150 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.996 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.920 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.542 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.856 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.076 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 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 60152e3c4c..9f36145455 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.zipeba92fe9-b7ba-4a30-b928-654b4429714f from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip3d748125-a20a-47a1-8324-db47c1b3e1c6 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 79c60bb8f8..600f5dd0e8 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
=================
-**00:46.492** total execution time for **how_to_extend_tvm** files:
+**00:47.737** 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``) | 00:43.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.332 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.370 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.376 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.014 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.021 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 8796e4dd8f..cba4d36265 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: 7006us [7006us] (46.58%; 46.58%)
- FoldScaleAxis: 8036us [6us] (53.42%; 53.42%)
- FoldConstant: 8029us [1658us] (53.38%; 99.92%)
- InferType: 6371us [6371us] (42.36%; 79.35%)
+ InferType: 7121us [7121us] (46.33%; 46.33%)
+ FoldScaleAxis: 8250us [6us] (53.67%; 53.67%)
+ FoldConstant: 8244us [1672us] (53.63%; 99.93%)
+ InferType: 6572us [6572us] (42.75%; 79.72%)
@@ -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: 6485us [6485us] (44.96%; 44.96%)
- FoldScaleAxis: 7939us [5us] (55.04%; 55.04%)
- FoldConstant: 7934us [1631us] (55.01%; 99.94%)
- InferType: 6303us [6303us] (43.70%; 79.45%)
+ InferType: 6615us [6615us] (45.04%; 45.04%)
+ FoldScaleAxis: 8072us [5us] (54.96%; 54.96%)
+ FoldConstant: 8067us [1650us] (54.93%; 99.94%)
+ InferType: 6417us [6417us] (43.69%; 79.55%)
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 e468a54895..fed7748c5f 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 48.046081 ms
+ Convolution: 54.112255 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 dd31840116..49ea95a1ba 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
@@ -659,7 +659,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.374019 ms
+ conv2d with tensor core: 11.913606 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 cc8269e34a..227491eed9 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: 0.018808
- Baseline: 3.429418
+ Numpy running time: 0.018163
+ Baseline: 3.201460
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.314154
+ Opt1: 0.298053
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.345004
+ Opt2: 0.328097
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.121400
+ Opt3: 0.112942
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109632
+ Opt4: 0.108599
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.109297
+ Opt5: 0.110638
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.144817
+ Opt6: 0.146956
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 b1b16e1b93..efe87c5001 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
=================
-**00:35.254** total execution time for **how_to_optimize_operators** files:
+**00:34.181** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.611 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.468 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.538 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.140 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.175 | 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 e3e3021b4f..2f52e8d6cf 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
=================
-**09:19.956** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:12.439** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:41.167 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:37.658 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.349 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.191 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.566 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.194 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:38.473 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:38.904 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.659 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.299 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.834 | 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 4d146a5910..becf15b937 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
@@ -242,581 +242,319 @@ cooperative fetching, unrolling and operator fusion.
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
- let cse_var_2: int32 = (rc.outer.outer*196)
- let cse_var_1: int32 = (rc.outer.outer*36)
+ for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_1: int32 = (rc.outer.outer*1568)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[(threadIdx.x_1*2)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*2), 81)) && (floormod((threadIdx.x_1*2), 81) < 72)) && (1 <= floormod((threadIdx.x_1*2), 9))) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 81)*49)) + (floordiv(floormod((threadIdx.x_1*2), 81), 9)*7)) + floormod((threadIdx.x_1*2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 1), 81)) && (floormod(((threadIdx.x_1*2) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 9))) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_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" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((threadIdx.x_1 < 48) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 30), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 30), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 73), 81)) && (floormod((threadIdx.x_1 + 73), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1288), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 73), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1344), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else((((threadIdx.x_1 < 49) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1400), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1456), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 6), 9)) && (floormod((threadIdx.x_1 + 54), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1512), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 6), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1624), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 60), 81)) && (floormod((threadIdx.x_1 + 60), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1680), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 35), 81)) && (floormod((threadIdx.x_1 + 35), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1736), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1792), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @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[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1848), 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" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 41), 81)) && (floormod((threadIdx.x_1 + 41), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1904), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 41), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2016), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2072)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 47), 81)) && (floormod((threadIdx.x_1 + 47), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2072), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 47), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else((((threadIdx.x_1 < 50) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2128), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 22), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2184)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 78), 81)) && (floormod((threadIdx.x_1 + 78), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2184), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 78), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2240), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2296)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 28), 81)) && (floormod((threadIdx.x_1 + 28), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2296), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 28), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2408)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2408), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @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[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2464), 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" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2520)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2520), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 1)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2576), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1[((threadIdx.x_1*2) + 112)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 31), 81)) && (floormod(((threadIdx.x_1*2) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 4), 9))) && (floormod(((threadIdx.x_1*2) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 112), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 31), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 113)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 32), 81)) && (floormod(((threadIdx.x_1*2) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 5), 9))) && (floormod(((threadIdx.x_1*2) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 113), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 32), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 224)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 62), 81)) && (floormod(((threadIdx.x_1*2) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 8), 9))) && (floormod(((threadIdx.x_1*2) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 224), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 62), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 225)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 9) + 7), 9)) && (floormod(((threadIdx.x_1*2) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*2), 9))) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 225), 81)*49)) + (floormod((floordiv((threadIdx.x_1*2), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*2), 9)) - 8)], 0f32, dtype=float32)
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48))] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*16)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.oute [...]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 1)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*16)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 2)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*16)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 4)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 5)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 7)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 8)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 10)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 11)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 13)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 14)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 16)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 17)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 19)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 20)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 22)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 23)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 8), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 25)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 8), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 26)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 8), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 3), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 28)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 3), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 29)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 3), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 10), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 31)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 10), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 32)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 10), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 11), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 34)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 11), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 35)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 11), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 36)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 4), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 37)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 4), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 38)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 4), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 39)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 13), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 40)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 13), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 41)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 13), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 42)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 14), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 43)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 14), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 44)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 14), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 45)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 5), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 46)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 5), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 47)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 5), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
}
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ for (rc.outer.inner: int32, 0, 2) {
+ for (ry.outer.inner: int32, 0, 3) {
+ for (rx.outer.inner: int32, 0, 3) {
+ for (xx.outer.inner: int32, 0, 7) {
+ let cse_var_2: int32 = (xx.outer.inner + 7)
+ {
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 648)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 648)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 729)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 729)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 810)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 810)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 891)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 891)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 972)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 972)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1053)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1053)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1134)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1134)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1215)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1215)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ }
+ }
+ }
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
}
}
for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -871,7 +609,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.208 ms
+ Execution time of this operator: 0.261 ms
@@ -919,8 +657,8 @@ 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=2)
+ 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=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
@@ -928,15 +666,15 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ 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=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
@@ -947,9 +685,9 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -966,16 +704,16 @@ 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=1)
+ 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=48)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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=2)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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:
@@ -995,561 +733,265 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#endif
extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[324];
- __shared__ float kernel_shared[576];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = (((((9 <= ((((int)threadIdx.x) * 2) % 81)) && (((((int)threadIdx.x) * 2) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 2) / 81) * 49)) + ((((((int)threadIdx.x) * 2) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((((9 <= (((((int)threadIdx.x) * 2) + 1) % 81)) && ((((((int)threadIdx.x) * 2) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 112)] = (((((9 <= (((((int)threadIdx.x) * 2) + 31) % 81)) && ((((((int)threadIdx.x) * 2) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 112) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 31) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 113)] = (((((9 <= (((((int)threadIdx.x) * 2) + 32) % 81)) && ((((((int)threadIdx.x) * 2) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 113) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 32) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 224)] = (((((9 <= (((((int)threadIdx.x) * 2) + 62) % 81)) && ((((((int)threadIdx.x) * 2) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 224) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 225)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 2) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 225) / 81) * 49)) + (((((((int)threadIdx.x) * 2) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 64512)];
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + (((((int)threadIdx.x) + 24) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((4 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + (((((int)threadIdx.x) + 5) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + (((((int)threadIdx.x) + 11) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((9 <= ((((int)threadIdx.x) + 73) % 81)) && (((((int)threadIdx.x) + 73) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 81) * 49)) + ((((((int)threadIdx.x) + 73) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = ((((((int)threadIdx.x) < 49) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= (((((int)threadIdx.x) / 9) + 6) % 9)) && (((((int)threadIdx.x) + 54) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1512) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 6) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((9 <= ((((int)threadIdx.x) + 60) % 81)) && (((((int)threadIdx.x) + 60) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 81) * 49)) + ((((((int)threadIdx.x) + 60) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((9 <= ((((int)threadIdx.x) + 35) % 81)) && (((((int)threadIdx.x) + 35) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 81) * 49)) + ((((((int)threadIdx.x) + 35) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1848) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((9 <= ((((int)threadIdx.x) + 41) % 81)) && (((((int)threadIdx.x) + 41) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 81) * 49)) + ((((((int)threadIdx.x) + 41) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + (((((int)threadIdx.x) + 16) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2072)] = (((((9 <= ((((int)threadIdx.x) + 47) % 81)) && (((((int)threadIdx.x) + 47) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2072) / 81) * 49)) + ((((((int)threadIdx.x) + 47) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = ((((((int)threadIdx.x) < 50) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2128) / 81) * 49)) + (((((int)threadIdx.x) + 22) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2184)] = (((((9 <= ((((int)threadIdx.x) + 78) % 81)) && (((((int)threadIdx.x) + 78) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2184) / 81) * 49)) + ((((((int)threadIdx.x) + 78) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2296)] = (((((9 <= ((((int)threadIdx.x) + 28) % 81)) && (((((int)threadIdx.x) + 28) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2296) / 81) * 49)) + ((((((int)threadIdx.x) + 28) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2408)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2408) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((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 * 1568) + (((((int)threadIdx.x) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2520)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2520) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2576) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48))] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 16)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 16)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 16)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 5)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 7)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 10)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 11)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 13)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 14)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 16)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 17)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 19)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 20)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 22)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 23)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 8) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 25)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 8) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 26)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 8) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 3) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 28)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 3) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 29)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 3) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 10) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 31)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 10) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 32)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 10) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 11) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 34)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 11) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 35)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 11) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 36)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 4) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 37)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 4) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 38)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 4) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 39)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 13) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 40)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 13) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 41)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 13) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 42)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 14) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 43)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 14) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 44)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 14) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 45)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 5) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 46)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 5) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 47)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 5) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ }
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 648)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 648)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 729)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 729)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 810)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 810)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 891)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 891)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 972)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 972)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1053)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1053)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1134)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1134)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1215)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1215)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ }
+ }
+ }
+ }
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -1611,7 +1053,7 @@ 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 41.167 seconds)
+ **Total running time of the script:** ( 5 minutes 37.658 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 315b227fe6..cdf3b905e1 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)
- 8.2442 8.2451 8.2605 8.2271 0.0136
+ 8.1684 8.1745 8.1780 8.1528 0.0111
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.566 seconds)
+ **Total running time of the script:** ( 1 minutes 2.194 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 fc41113143..ed6ae9c1f1 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)
- 761.5858 761.5612 761.9018 761.2943 0.2486
+ 749.1891 749.6458 751.5422 746.3793 2.1323
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.349 seconds)
+ **Total running time of the script:** ( 1 minutes 31.191 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 2a47b7d599..52a462a079 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
@@ -386,59 +386,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 16)
- let cse_var_1: int32 = (i.outer.inner*8)
- {
- compute_5: Buffer(compute_4, float32, [128], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (cse_var_1 + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_4: int32 = (cse_var_1 + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_5: int32 = (cse_var_1 + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_6: int32 = (cse_var_1 + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_7: int32 = (cse_var_1 + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_8: int32 = (cse_var_1 + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_9: int32 = (cse_var_1 + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [256], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_10: int32 = ((i0.inner*512) + i0.outer.i1.outer.fused)
- compute[cse_var_10] = max((compute_5[i0.inner] + placeholder_4[cse_var_10]), 0f32)
+ for (i0.inner: int32, 0, 8) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -494,7 +465,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 4.086 ms
+ Execution time of this operator: 1.599 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 08281bd902..1c291214dc 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:42.994** total execution time for **how_to_tune_with_autotvm** files:
+**00:40.308** 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``) | 00:42.960 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:40.272 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 c1539f2539..7ca12fb6f0 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
@@ -265,8 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 6.15/6.15 result: MeasureResult(costs=(0.03765760025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.275269031524658, timestamp=1668492496.9377825) [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,626203
- No: 2 GFLOPS: 0.00/6.15 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -388,10 +387,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2967214
- No: 3 GFLOPS: 7.94/7.94 result: MeasureResult(costs=(0.029165311750000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8207025527954102, timestamp=1668492498.5616288) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2087599
- No: 4 GFLOPS: 178.18/178.18 result: MeasureResult(costs=(0.001299231987012987,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7496528625488281, timestamp=1668492500.1057882) [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4261770
- No: 5 GFLOPS: 0.00/178.18 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9666825
+ No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -513,163 +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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8350362
- No: 6 GFLOPS: 205.86/205.86 result: MeasureResult(costs=(0.0011245512342342343,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.502927303314209, timestamp=1668492504.893299) [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6076876
- No: 7 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007ff6a869dfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
- Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1978908
- No: 8 GFLOPS: 115.47/205.86 result: MeasureResult(costs=(0.0020049101200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.099451780319214, timestamp=1668492510.9292245) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8236475
- No: 9 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1217071
+ No: 3 GFLOPS: 31.16/31.16 result: MeasureResult(costs=(0.007428685857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8253495693206787, timestamp=1668512663.8954246) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1051435
+ No: 4 GFLOPS: 0.00/31.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -791,8 +634,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8032009
- No: 10 GFLOPS: 0.00/205.86 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, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10044682
+ No: 5 GFLOPS: 8.87/31.16 result: MeasureResult(costs=(0.026085815249999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.142474889755249, timestamp=1668512673.1282887) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8794587
+ No: 6 GFLOPS: 0.00/31.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -914,8 +758,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7356517
- No: 11 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1715554
+ No: 7 GFLOPS: 0.00/31.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1037,8 +881,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5763691
- No: 12 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9211582
+ No: 8 GFLOPS: 212.05/212.05 result: MeasureResult(costs=(0.0010917095714285713,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5799691677093506, timestamp=1668512674.066223) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1951455
+ No: 9 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1160,9 +1005,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4804238
- No: 13 GFLOPS: 152.73/205.86 result: MeasureResult(costs=(0.0015157305000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.202910900115967, timestamp=1668492516.5718539) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7464226
- No: 14 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,765924
+ No: 10 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1284,8 +1128,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4857815
- No: 15 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7085674
+ No: 11 GFLOPS: 4.58/212.05 result: MeasureResult(costs=(0.05049862275,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4923033714294434, timestamp=1668512675.7578967) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,996160
+ No: 12 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1407,8 +1252,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1960765
- No: 16 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1570957
+ No: 13 GFLOPS: 67.57/212.05 result: MeasureResult(costs=(0.0034263342571428574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5604088306427002, timestamp=1668512679.5054412) [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5273534
+ No: 14 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1530,8 +1376,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,901418
- No: 17 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1151557
+ No: 15 GFLOPS: 106.35/212.05 result: MeasureResult(costs=(0.002176714347826087,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.306579351425171, timestamp=1668512680.1356115) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2451920
+ No: 16 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -1619,7 +1466,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f9583403fa2
+ 12: 0x00007fdf4c19afa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -1683,8 +1530,8 @@ for this template
22: _PyEval_EvalFrameDefault
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8340166
- No: 18 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ 19: _PyFunction_FastCall [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,974519
+ No: 17 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1806,8 +1653,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3153633
- No: 19 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8493371
+ No: 18 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1929,8 +1776,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,756836
- No: 20 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10056444
+ No: 19 GFLOPS: 341.57/341.57 result: MeasureResult(costs=(0.0006777660743243244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9776229858398438, timestamp=1668512685.8448713) [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4108374
+ No: 20 GFLOPS: 0.00/341.57 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2052,7 +1900,7 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6791120
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10170862
@@ -2107,9 +1955,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6076876
+ [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4108374
Finish loading 20 records
- Time cost of this operator: 0.001368
+ Time cost of this operator: 0.001069
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 cd97dd617d..ec0bdfde03 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
@@ -327,10 +327,10 @@ 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 314.1 98.58 (1, 2, 10, 10, 3) 2 1 [314.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.559 1.117 (1, 6, 10, 10) 1 1 [3.559]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.303 (1, 1, 10, 10, 3) 1 1 [0.964]
- Total_time - 318.623 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.5 98.731 (1, 2, 10, 10, 3) 2 1 [311.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.957 (1, 6, 10, 10) 1 1 [3.021]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.312 (1, 1, 10, 10, 3) 1 1 [0.984]
+ Total_time - 315.505 - - - - -
@@ -394,10 +394,10 @@ 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 103.3 97.531 (1, 6, 10, 10, 1) 2 1 [103.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.774 1.675 (1, 6, 10, 10) 1 1 [1.774]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.793 (1, 3, 10, 10, 1) 1 1 [0.84]
- Total_time - 105.915 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 101.3 97.366 (1, 6, 10, 10, 1) 2 1 [101.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.696 (1, 6, 10, 10) 1 1 [1.765]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.938 (1, 1, 10, 10, 3) 1 1 [0.976]
+ Total_time - 104.041 - - - - -
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 4eb8591604..7753bc5e16 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, 48.9MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
29%|##9 | 1.00M/3.42M [00:00<00:00, 10.4MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 26.0MB/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 3.137 seconds)
+ **Total running time of the script:** ( 1 minutes 1.016 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 94669ea1b2..ecbb939f33 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/tmpv9m_xlv4/images/random'
+ '/tmp/tmppttw5wrc/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], [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]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
: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/tmpv9m_xlv4/images/target contains 8144 images
- /tmp/tmpv9m_xlv4/images/random contains 5000 images
+ /tmp/tmppttw5wrc/images/target contains 8144 images
+ /tmp/tmppttw5wrc/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: 0.2101 - accuracy: 0.9251 - val_loss: 0.1412 - val_accuracy: 0.9592 - 47s/epoch - 144ms/step
+ 328/328 - 46s - loss: 0.2159 - accuracy: 0.9249 - val_loss: 0.1130 - val_accuracy: 0.9585 - 46s/epoch - 141ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0943 - accuracy: 0.9650 - val_loss: 0.0996 - val_accuracy: 0.9690 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0959 - accuracy: 0.9662 - val_loss: 0.1393 - val_accuracy: 0.9498 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0668 - accuracy: 0.9759 - val_loss: 0.1160 - val_accuracy: 0.9690 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0740 - accuracy: 0.9727 - val_loss: 0.1125 - val_accuracy: 0.9626 - 43s/epoch - 130ms/step
- <keras.callbacks.History object at 0x7fd545ade990>
+ <keras.callbacks.History object at 0x7f7752820f90>
@@ -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 45.497 seconds)
+ **Total running time of the script:** ( 4 minutes 31.174 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 a6076de4c2..3c23a921d9 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
=================
-**06:51.087** total execution time for **how_to_work_with_microtvm** files:
+**06:32.444** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:45.497 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:31.174 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:03.137 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:01.016 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.145 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:48.255 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.263 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.803 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.734 | 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 7b66cf9ac7..3fbe12960c 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:42.112** total execution time for **how_to_work_with_relay** files:
+**00:43.186** 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``) | 00:31.962 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.569 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:08.729 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.075 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.414 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.536 | 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 2c1bbd5d4b..a0c4a4b6c0 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 0x7fd5a0aca3b0>
+ <function my_cuda_math_rule at 0x7f7752aa3b00>
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 dac55c67a0..7bd2f04441 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
=================
-**00:08.082** total execution time for **how_to_work_with_schedules** files:
+**00:04.756** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.699 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.357 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.046 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.053 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.577 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.561 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.113 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.048 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.018 | 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 dfe9526b76..89defd6e70 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpaz957g8n/input0.cc'\nsource_filename = \"/tmp/tmpaz957g8n/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/tmpokfjtees/input0.cc'\nsource_filename = \"/tmp/tmpokfjtees/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 afd80f345b..73bb409c8e 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
=================
-**00:26.434** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.414** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.428 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.408 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 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 b00cd687c5..7698a4ffac 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 28.76s!
+ resnet18_v1 inference graph built in 28.42s!
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 00eb4dba3b..108a0f946a 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 19.78s!
+ yolov3-tiny inference graph built in 19.45s!
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 55a583a76c..3e7d7fa5ef 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
=================
-**01:40.714** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.545** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.093 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.621 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.504 | 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 bfe40c1200..12e60b34d9 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
=================
-**00:03.142** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.226** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.695 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.763 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.447 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.463 | 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 a4ddac754f..af0222771c 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
=================
-**00:00.792** total execution time for **topic_vta_tutorials** files:
+**00:00.824** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.425 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.438 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.367 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.386 | 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 24fa807538..df553678f4 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+
+ *E
+
@@ -326,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.465 ms
+ Execution time of this operator: 99.230 ms
@@ -444,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.679 seconds)
+ **Total running time of the script:** ( 1 minutes 29.607 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 68f6a13a58..ff0bea219b 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: 0.94/0.94 result: MeasureResult(costs=(0.28453201939999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.70817494392395, timestamp=1668491114.0931864) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
- No: 2 GFLOPS: 12.68/12.68 result: MeasureResult(costs=(0.0211742646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5676043033599854, timestamp=1668491115.3570225) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
- No: 3 GFLOPS: 14.74/14.74 result: MeasureResult(costs=(0.01821234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7354567050933838, timestamp=1668491115.8122365) [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
- No: 4 GFLOPS: 3.15/14.74 result: MeasureResult(costs=(0.08535189400000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5294511318206787, timestamp=1668491118.093534) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
- No: 5 GFLOPS: 1.15/14.74 result: MeasureResult(costs=(0.23308930180000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9469738006591797, timestamp=1668491122.1903) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
- No: 6 GFLOPS: 10.84/14.74 result: MeasureResult(costs=(0.0247700522,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5869479179382324, timestamp=1668491122.7561338) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
- No: 7 GFLOPS: 11.45/14.74 result: MeasureResult(costs=(0.0234400864,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5295507907867432, timestamp=1668491124.04584) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
- No: 8 GFLOPS: 0.50/14.74 result: MeasureResult(costs=(0.5341811477999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.7483389377594, timestamp=1668491132.7990813) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
- No: 9 GFLOPS: 2.11/14.74 result: MeasureResult(costs=(0.12725059519999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1597647666931152, timestamp=1668491135.0713344) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
- No: 10 GFLOPS: 1.81/14.74 result: MeasureResult(costs=(0.1483948042,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4889540672302246, timestamp=1668491137.6169114) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 1 GFLOPS: 12.79/12.79 result: MeasureResult(costs=(0.020986933,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.49678730964660645, timestamp=1668511322.0002625) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
+ No: 2 GFLOPS: 10.73/12.79 result: MeasureResult(costs=(0.0250120642,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5861332416534424, timestamp=1668511322.608602) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+ No: 3 GFLOPS: 0.51/12.79 result: MeasureResult(costs=(0.527322839,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.61455512046814, timestamp=1668511331.9650085) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+ No: 4 GFLOPS: 9.10/12.79 result: MeasureResult(costs=(0.029512603000000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8305795192718506, timestamp=1668511333.3291118) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+ No: 5 GFLOPS: 9.58/12.79 result: MeasureResult(costs=(0.0280191888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5838408470153809, timestamp=1668511334.0774398) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+ No: 6 GFLOPS: 11.67/12.79 result: MeasureResult(costs=(0.0230074138,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5560197830200195, timestamp=1668511334.6127582) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+ No: 7 GFLOPS: 8.25/12.79 result: MeasureResult(costs=(0.0325430638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6715357303619385, timestamp=1668511336.0187078) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+ No: 8 GFLOPS: 3.07/12.79 result: MeasureResult(costs=(0.08744604240000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5885965824127197, timestamp=1668511337.6198728) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+ No: 9 GFLOPS: 8.36/12.79 result: MeasureResult(costs=(0.0321037958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6911242008209229, timestamp=1668511338.4238167) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
+ No: 10 GFLOPS: 11.13/12.79 result: MeasureResult(costs=(0.0241191274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5254871845245361, timestamp=1668511338.9775114) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 5b89063ec6..76c792f0d9 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': 509.33978959999877, 'median': 509.0096936000009, 'std': 2.4713246779646143}
+ {'mean': 512.5842140299937, 'median': 513.2335168000054, 'std': 2.1297284277345603}
@@ -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: 6.99/ 14.73 GFLOPS | Progress: (4/20) | 10.87 s
[Task 1/25] Current/Best: 5.78/ 23.03 GFLOPS | Progress: (8/20) | 14.80 s
[Task 1/25] Current/Best: 12.06/ 23.03 GFLOPS | Progress: (12/20) | 16.92 s
[Task 1/25] Current/Best: 12.88/ 23.03 GFLOPS | Progress: (16/20) | 18.66 s
[Task 1/25] Current/Best: 13.77/ 23.03 GFLOPS | Progress: (20/20) | 21.83 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 19.10/ 19.10 GFLOPS | Progress: (4/20) | 3.06 s
[Task 2/25] Current/Best: 15.95/ 19.30 GFLOPS | Progress: (8/20) | 4.32 s
[Task 2/25] Current/Best: 12.19/ 19.30 GFLOPS | Progress: (12/20) | 5.74 s
[Task 2/25] Current/Best: 10.64/ 19.30 GFLOPS | Progress: (16/20) | 7.06 s
[Task 2/25] Current/Best: 10.14/ 19.30 GFLOPS | Progress: (20/20) | 10.06 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 3.15/ 16.33 GFLOPS | Progress: (4/20) | 4.15 s
[Task 3/25] Current/Best: 13.89/ 21.09 GFLOPS | Progress: (8/20) | 6.11 s
[Task 3/25] Current/Best: 14.02/ 21.09 GFLOPS | Progress: (12/20) | 8.18 s
[Task 3/25] Current/Best: 17.47/ 21.09 GFLOPS | Progress: (16/20) | 12.70 s
[Task 3/25] Current/Best: 11.51/ 21.09 GFLOPS | Progress: (20/20) | 14.50 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.85/ 21.31 GFLOPS | Progress: (4/20) | 7.17 s
[Task 4/25] Current/Best: 14.23/ 21.31 GFLOPS | Progress: (8/20) | 9.16 s
[Task 4/25] Current/Best: 14.84/ 21.31 GFLOPS | Progress: (12/20) | 13.77 s
[Task 4/25] Current/Best: 20.72/ 21.31 GFLOPS | Progress: (16/20) | 15.49 s
[Task 4/25] Current/Best: 9.74/ 21.31 GFLOPS | Progress: (20/20) | 20.67 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 10.71/ 15.71 GFLOPS | Progress: (4/20) | 3.28 s
[Task 5/25] Current/Best: 15.83/ 18.23 GFLOPS | Progress: (8/20) | 5.08 s
[Task 5/25] Current/Best: 5.48/ 19.27 GFLOPS | Progress: (12/20) | 8.02 s
[Task 5/25] Current/Best: 14.15/ 19.27 GFLOPS | Progress: (16/20) | 9.61 s
[Task 5/25] Current/Best: 4.47/ 19.27 GFLOPS | Progress: (20/20) | 11.73 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 15.27/ 15.30 GFLOPS | Progress: (4/20) | 4.23 s
[Task 6/25] Current/Best: 11.93/ 19.05 GFLOPS | Progress: (8/20) | 7.81 s
[Task 6/25] Current/Best: 5.78/ 19.05 GFLOPS | Progress: (12/20) | 10.94 s
[Task 6/25] Current/Best: 12.94/ 20.87 GFLOPS | Progress: (16/20) | 12.84 s
[Task 6/25] Current/Best: 16.19/ 20.87 GFLOPS | Progress: (20/20) | 15.69 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 3.57 s
[Task 7/25] Current/Best: 15.67/ 17.53 GFLOPS | Progress: (8/20) | 5.63 s
[Task 7/25] Current/Best: 15.58/ 19.15 GFLOPS | Progress: (12/20) | 7.26 s
[Task 7/25] Current/Best: 21.89/ 22.43 GFLOPS | Progress: (16/20) | 8.95 s
[Task 7/25] Current/Best: 14.61/ 22.43 GFLOPS | Progress: (20/20) | 11.71 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.55/ 15.42 GFLOPS | Progress: (4/20) | 4.68 s
[Task 8/25] Current/Best: 11.49/ 15.42 GFLOPS | Progress: (8/20) | 7.02 s
[Task 8/25] Current/Best: 10.78/ 15.42 GFLOPS | Progress: (12/20) | 14.16 s
[Task 8/25] Current/Best: 17.80/ 17.80 GFLOPS | Progress: (16/20) | 16.58 s
[Task 8/25] Current/Best: 12.25/ 17.80 GFLOPS | Progress: (20/20) | 27.45 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.76/ 14.46 GFLOPS | Progress: (4/20) | 7.32 s
[Task 9/25] Current/Best: 22.24/ 22.24 GFLOPS | Progress: (8/20) | 8.60 s
[Task 9/25] Current/Best: 6.48/ 22.24 GFLOPS | Progress: (12/20) | 12.37 s
[Task 9/25] Current/Best: 17.58/ 22.24 GFLOPS | Progress: (16/20) | 18.48 s
[Task 9/25] Current/Best: 11.61/ 22.24 GFLOPS | Progress: (20/20
) | 22.80 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 14.13/ 19.07 GFLOPS | Progress: (4/20) | 2.96 s
[Task 10/25] Current/Best: 12.45/ 19.07 GFLOPS | Progress: (8/20) | 5.27 s
[Task 10/25] Current/Best: 10.37/ 19.07 GFLOPS | Progress: (12/20) | 7.06 s
[Task 10/25] Current/Best: 10.99/ 19.07 GFLOPS | Progress: (16/20) | 9.66 s
[Task 10/25] Current/Best: 4.35/ 19.07 GFLOPS | Progress: (20/20) | 11.23 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.54/ 12.42 GFLOPS | Progress: (4/20) | 4.17 s
[Task 11/25] Current/Best: 3.17/ 18.81 GFLOPS | Progress: (8/20) | 6.65 s
[Task 11/25] Current/Best: 13.89/ 18.81 GFLOPS | Progress: (12/20) | 9.01 s
[Task 11/25] Current/Best: 9.88/ 18.81 GFLOPS | Progress: (16/20) | 10.86 s
[Task 11/25] Current/Best: 8.40/ 18.89 GFLOPS | Progress: (20/20) | 13.13 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.86/ 14.35 GFLOPS | Progress: (4/20) | 3.91 s
[Task 12/25] Current/Best: 12.58/ 14.35 GFLOPS | Progress: (8/20) | 9.68 s
[Task 12/25] Current/Best: 12.28/ 16.66 GFLOPS | Progress: (12/20) | 18.57 s
[Task 12/25] Current/Best: 11.15/ 16.66 GFLOPS | Progress: (16/20) | 20.67 s
[Task 12/25] Current/Best: 6.02/ 21.36 GFLOPS | Progress: (20/20) | 22.84 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 6.26/ 14.04 GFLOPS | Progress: (4/20) | 4.82 s
[Task 13/25] Current/Best: 11.21/ 14.04 GFLOPS | Progress: (8/20) | 8.28 s
[Task 13/25] Current/Best: 8.71/ 21.17 GFLOPS | Progress: (12/20) | 10.22 s
[Task 13/25] Current/Best: 16.94/ 21.17 GFLOPS | Progress: (16/20) | 12.34 s
[Task 13/25] Current/Best: 5.93/ 21.17 GFLOPS | Progress: (20/20) | 14.77 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 1.53/ 14.75 GFLOPS | Progress: (4/20) | 5.77 s
[Task 14/25] Current/Best: 9.68/ 14.75 GFLOPS | Progress: (8/20) | 10.23 s
[Task 14/25] Current/Best: 13.13/ 14.75 GFLOPS | Progress: (12/20) | 12.14 s
[Task 14/25] Current/Best: 2.78/ 14.75 GFLOPS | Progress: (16/20) | 17.80 s Done.
-
[Task 14/25] Current/Best: 14.76/ 14.76 GFLOPS | Progress: (20/20) | 20.31 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 17.45/ 20.78 GFLOPS | Progress: (4/20) | 2.85 s
[Task 15/25] Current/Best: 21.02/ 21.02 GFLOPS | Progress: (8/20) | 6.69 s
[Task 15/25] Current/Best: 22.63/ 22.63 GFLOPS | Progress: (12/20) | 8.91 s
[Task 15/25] Current/Best: 16.76/ 22.63 GFLOPS | Progress: (16/20) | 10.75 s
[Task 15/25] Current/Best: 12.12/ 22.63 GFLOPS | Progress: (20/20) | 12.11 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 4.33/ 14.13 GFLOPS | Progress: (4/20) | 4.02 s
[Task 16/25] Current/Best: 10.56/ 14.32 GFLOPS | Progress: (8/20) | 7.50 s
[Task 16/25] Current/Best: 4.66/ 16.14 GFLOPS | Progress: (12/20) | 9.38 s
[Task 16/25] Current/Best: 10.03/ 16.14 GFLOPS | Progress: (16/20) | 10.73 s
[Task 16/25] Current/Best: 6.17/ 16.17 GFLOPS | Progress: (20/20)
| 12.35 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 15.70/ 19.12 GFLOPS | Progress: (4/20) | 4.66 s
[Task 17/25] Current/Best: 19.05/ 20.36 GFLOPS | Progress: (8/20) | 6.68 s
[Task 17/25] Current/Best: 10.14/ 20.36 GFLOPS | Progress: (12/20) | 8.94 s
[Task 17/25] Current/Best: 10.20/ 20.36 GFLOPS | Progress: (16/20) | 11.42 s
[Task 17/25] Current/Best: 22.83/ 22.83 GFLOPS | Progress: (20/20) | 13.68 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.80/ 14.08 GFLOPS | Progress: (4/20) | 7.52 s
[Task 18/25] Current/Best: 10.34/ 18.02 GFLOPS | Progress: (8/20) | 11.91 s
[Task 18/25] Current/Best: 3.11/ 19.97 GFLOPS | Progress: (12/20) | 14.10 s
[Task 18/25] Current/Best: 9.55/ 19.97 GFLOPS | Progress: (16/20) | 18.24 s
[Task 18/25] Current/Best: 9.14/ 20.39 GFLOPS | Progress: (20/20) | 20.03 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.67/ 21.08 GFLOPS | Progress: (4/20) | 4.78 s
[Task 19/25] Current/Best: 11.20/ 21.08 GFLOPS | Progress: (8/20) | 8.18 s
[Task 19/25] Current/Best: 11.11/ 21.08 GFLOPS | Progress: (12/20) | 10.79 s
[Task 19/25] Current/Best: 12.76/ 21.08 GFLOPS | Progress: (16/20) | 13.56 s
[Task 19/25] Current/Best: 11.10/ 21.08 GFLOPS | Progress: (20/20) | 16.20 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 4.73/ 15.87 GFLOPS | Progress: (4/20) | 3.46 s
[Task 20/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (8/20) | 5.58 s
[Task 20/25] Current/Best: 7.80/ 20.63 GFLOPS | Progress: (12/20) | 9.86 s Done.
-
[Task 20/25] Current/Best: 14.72/ 20.63 GFLOPS | Progress: (16/20) | 13.09 s
[Task 20/25] Current/Best: 7.84/ 20.63 GFLOPS | Progress: (20/20) | 15.49 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 15.77/ 15.77 GFLOPS | Progress: (4/20) | 2.83 s
[Task 21/25] Current/Best: 18.00/ 18.00 GFLOPS | Progress: (8/20) | 5.15 s
[Task 21/25] Current/Best: 5.41/ 19.10 GFLOPS | Progress: (12/20) | 8.04 s
[Task 21/25] Current/Best: 7.75/ 19.10 GFLOPS | Progress: (16/20) | 10.07 s
[Task 21/25] Current/Best: 18.37/ 19.10 GFLOPS | Progress: (20/20) | 11.36 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 16.82/ 22.23 GFLOPS | Progress: (4/20) | 3.98 s
[Task 22/25] Current/Best: 11.42/ 22.23 GFLOPS | Progress: (8/20) | 5.91 s
[Task 22/25] Current/Best: 9.54/ 22.23 GFLOPS | Progress: (12/20) | 7.45 s
[Task 22/25] Current/Best: 16.32/ 22.23 GFLOPS | Progress: (16/20) | 8.71 s
[Task 22/25] Current/Best: 6.02/ 22.23 GFLOPS | Progress: (20/20) |
11.70 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 11.26/ 17.23 GFLOPS | Progress: (4/20) | 4.29 s
[Task 23/25] Current/Best: 12.17/ 19.54 GFLOPS | Progress: (8/20) | 7.04 s
[Task 23/25] Current/Best: 13.59/ 19.54 GFLOPS | Progress: (12/20) | 11.61 s
[Task 23/25] Current/Best: 18.74/ 19.54 GFLOPS | Progress: (16/20) | 14.02 s
[Task 23/25] Current/Best: 10.23/ 19.54 GFLOPS | Progress: (20/20) | 15.96 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.32/ 5.25 GFLOPS | Progress: (4/20) | 12.23 s
[Task 24/25] Current/Best: 1.72/ 7.94 GFLOPS | Progress: (8/20) | 18.15 s
[Task 24/25] Current/Best: 7.83/ 7.94 GFLOPS | Progress: (12/20) | 28.84 s
[Task 24/25] Current/Best: 7.93/ 7.94 GFLOPS | Progress: (16/20) | 39.57 s
[Task 24/25] Current/Best: 7.82/ 9.95 GFLOPS | Progress: (20/20) | 41.36 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 14.81/ 17.70 GFLOPS | Progress: (4/20) | 7.00 s
[Task 1/25] Current/Best: 7.47/ 17.70 GFLOPS | Progress: (8/20) | 10.80 s
[Task 1/25] Current/Best: 14.30/ 17.70 GFLOPS | Progress: (12/20) | 13.02 s
[Task 1/25] Current/Best: 23.01/ 23.01 GFLOPS | Progress: (16/20) | 14.88 s
[Task 1/25] Current/Best: 13.25/ 23.01 GFLOPS | Progress: (20/20) | 17.83 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 19.64/ 19.91 GFLOPS | Progress: (4/20) | 3.15 s
[Task 2/25] Current/Best: 8.62/ 19.91 GFLOPS | Progress: (8/20) | 4.25 s
[Task 2/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (12/20) | 5.39 s
[Task 2/25] Current/Best: 11.20/ 20.72 GFLOPS | Progress: (16/20) | 6.96 s
[Task 2/25] Current/Best: 15.03/ 20.72 GFLOPS | Progress: (20/20) | 7.96 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 3.11/ 23.65 GFLOPS | Progress: (4/20) | 3.86 s
[Task 3/25] Current/Best: 6.94/ 23.65 GFLOPS | Progress: (8/20) | 6.09 s
[Task 3/25] Current/Best: 14.07/ 23.65 GFLOPS | Progress: (12/20) | 8.88 s
[Task 3/25] Current/Best: 14.52/ 23.65 GFLOPS | Progress: (16/20) | 10.86 s
[Task 3/25] Current/Best: 12.76/ 23.65 GFLOPS | Progress: (20/20) | 12.91 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (4/20) | 5.15 s
[Task 4/25] Current/Best: 20.99/ 20.99 GFLOPS | Progress: (8/20) | 10.03 s
[Task 4/25] Current/Best: 12.16/ 20.99 GFLOPS | Progress: (12/20) | 14.53 s
[Task 4/25] Current/Best: 14.19/ 20.99 GFLOPS | Progress: (16/20) | 16.22 s
[Task 4/25] Current/Best: 14.31/ 20.99 GFLOPS | Progress: (20/20) | 18.77 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 6.69/ 13.60 GFLOPS | Progress: (4/20) | 3.46 s
[Task 5/25] Current/Best: 5.54/ 14.82 GFLOPS | Progress: (8/20) | 5.66 s
[Task 5/25] Current/Best: 4.08/ 14.82 GFLOPS | Progress: (12/20) | 7.69 s
[Task 5/25] Current/Best: 14.20/ 14.82 GFLOPS | Progress: (16/20) | 11.14 s
[Task 5/25] Current/Best: 6.43/ 20.28 GFLOPS | Progress: (20/20) | 13.06 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.71/ 22.72 GFLOPS | Progress: (4/20) | 3.52 s
[Task 6/25] Current/Best: 5.29/ 22.72 GFLOPS | Progress: (8/20) | 7.00 s
[Task 6/25] Current/Best: 18.13/ 22.72 GFLOPS | Progress: (12/20) | 9.37 s
[Task 6/25] Current/Best: 12.77/ 22.72 GFLOPS | Progress: (16/20) | 12.12 s
[Task 6/25] Current/Best: 2.88/ 22.72 GFLOPS | Progress: (20/20) | 15.35 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 13.38/ 17.92 GFLOPS | Progress: (4/20) | 3.56 s
[Task 7/25] Current/Best: 18.67/ 18.67 GFLOPS | Progress: (8/20) | 5.49 s
[Task 7/25] Current/Best: 12.21/ 18.67 GFLOPS | Progress: (12/20) | 7.81 s
[Task 7/25] Current/Best: 11.90/ 18.67 GFLOPS | Progress: (16/20) | 10.37 s
[Task 7/25] Current/Best: 9.62/ 18.67 GFLOPS | Progress: (20/20) | 12.60 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 14.79/ 20.43 GFLOPS | Progress: (4/20) | 3.25 s
[Task 8/25] Current/Best: 10.53/ 20.43 GFLOPS | Progress: (8/20) | 14.08 s
[Task 8/25] Current/Best: 11.48/ 20.43 GFLOPS | Progress: (12/20) | 16.60 s
[Task 8/25] Current/Best: 5.44/ 20.43 GFLOPS | Progress: (16/20) | 20.25 s
[Task 8/25] Current/Best: 7.29/ 20.43 GFLOPS | Progress: (20/20) | 22.36 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.33/ 13.25 GFLOPS | Progress: (4/20) | 4.58 s
[Task 9/25] Current/Best: 20.35/ 20.39 GFLOPS | Progress: (8/20) | 14.90 s
[Task 9/25] Current/Best: 11.48/ 20.39 GFLOPS | Progress: (12/20) | 17.68 s
[Task 9/25] Current/Best: 13.91/ 20.39 GFLOPS | Progress: (16/20) | 28.42 s
[Task 9/25] Current/Best: 18.70/ 20.39 GFLOPS | Progress: (20/
20) | 39.31 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.56/ 20.48 GFLOPS | Progress: (4/20) | 2.79 s
[Task 10/25] Current/Best: 20.27/ 20.83 GFLOPS | Progress: (8/20) | 4.37 s
[Task 10/25] Current/Best: 13.13/ 20.83 GFLOPS | Progress: (12/20) | 6.77 s
[Task 10/25] Current/Best: 5.30/ 20.83 GFLOPS | Progress: (16/20) | 10.62 s
[Task 10/25] Current/Best: 11.38/ 20.83 GFLOPS | Progress: (20/20) | 12.36 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 13.20/ 13.20 GFLOPS | Progress: (4/20) | 4.66 s
[Task 11/25] Current/Best: 11.48/ 18.62 GFLOPS | Progress: (8/20) | 6.61 s Done.
Done.
-
[Task 25/25] Current/Best: 5.89/ 7.32 GFLOPS | Progress: (4/20) | 12.29 s
[Task 25/25] Current/Best: 9.38/ 9.38 GFLOPS | Progress: (8/20) | 20.57 s
[Task 25/25] Current/Best: 8.38/ 9.38 GFLOPS | Progress: (12/20) | 21.63 s
[Task 25/25] Current/Best: 6.09/ 9.38 GFLOPS | Progress: (16/20) | 22.74 s
[Task 25/25] Current/Best: 5.61/ 9.38 GFLOPS | Progress: (20/20) | 27.80 s
+
[Task 11/25] Current/Best: 22.87/ 22.87 GFLOPS | Progress: (12/20) | 9.40 s
[Task 11/25] Current/Best: 8.78/ 22.87 GFLOPS | Progress: (16/20) | 11.75 s
[Task 11/25] Current/Best: 6.25/ 22.87 GFLOPS | Progress: (20/20) | 14.10 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.60/ 18.68 GFLOPS | Progress: (4/20) | 3.91 s
[Task 12/25] Current/Best: 12.62/ 18.68 GFLOPS | Progress: (8/20) | 5.88 s
[Task 12/25] Current/Best: 12.96/ 18.68 GFLOPS | Progress: (12/20) | 9.91 s
[Task 12/25] Current/Best: 11.59/ 18.68 GFLOPS | Progress: (16/20) | 11.64 s
[Task 12/25] Current/Best: 15.08/ 18.68 GFLOPS | Progress: (20/20) | 13.52 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 6.17/ 20.50 GFLOPS | Progress: (4/20) | 5.29 s
[Task 13/25] Current/Best: 17.83/ 20.50 GFLOPS | Progress: (8/20) | 8.53 s
[Task 13/25] Current/Best: 19.44/ 20.50 GFLOPS | Progress: (12/20) | 11.79 s
[Task 13/25] Current/Best: 15.53/ 20.50 GFLOPS | Progress: (16/20) | 14.15 s
[Task 13/25] Current/Best: 13.39/ 20.50 GFLOPS | Progress: (20/20) | 16.10 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (4/20) | 3.61 s
[Task 14/25] Current/Best: 18.80/ 20.61 GFLOPS | Progress: (8/20) | 4.98 s
[Task 14/25] Current/Best: 15.17/ 20.61 GFLOPS | Progress: (12/20) | 8.18 s
[Task 14/25] Current/Best: 15.24/ 20.61 GFLOPS | Progress: (16/20) | 10.59 s
[Task 14/25] Current/Best: 8.42/ 20.61 GFLOPS | Progress: (20/20) | 14.64 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 4.85/ 17.95 GFLOPS | Progress: (4/20) | 4.34 s
[Task 15/25] Current/Best: 6.15/ 19.44 GFLOPS | Progress: (8/20) | 6.31 s
[Task 15/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (12/20) | 11.78 s
[Task 15/25] Current/Best: 4.14/ 19.51 GFLOPS | Progress: (16/20) | 13.40 s
[Task 15/25] Current/Best: 6.49/ 19.51 GFLOPS | Progress: (20/20)
| 16.06 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.24/ 12.69 GFLOPS | Progress: (4/20) | 4.61 s
[Task 16/25] Current/Best: 3.62/ 20.06 GFLOPS | Progress: (8/20) | 6.67 s
[Task 16/25] Current/Best: 14.45/ 20.06 GFLOPS | Progress: (12/20) | 8.27 s
[Task 16/25] Current/Best: 16.91/ 20.06 GFLOPS | Progress: (16/20) | 9.54 s
[Task 16/25] Current/Best: 18.25/ 20.06 GFLOPS | Progress: (20/20) | 11.08 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 1.56/ 18.45 GFLOPS | Progress: (4/20) | 5.20 s
[Task 17/25] Current/Best: 9.99/ 21.77 GFLOPS | Progress: (8/20) | 7.93 s Done.
+ Done.
+
[Task 17/25] Current/Best: 10.12/ 21.77 GFLOPS | Progress: (12/20) | 10.12 s
[Task 17/25] Current/Best: 12.25/ 21.77 GFLOPS | Progress: (16/20) | 12.71 s
[Task 17/25] Current/Best: 16.28/ 21.77 GFLOPS | Progress: (20/20) | 15.41 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.68/ 18.07 GFLOPS | Progress: (4/20) | 4.58 s
[Task 18/25] Current/Best: 16.03/ 18.07 GFLOPS | Progress: (8/20) | 6.36 s
[Task 18/25] Current/Best: 3.07/ 18.07 GFLOPS | Progress: (12/20) | 8.83 s
[Task 18/25] Current/Best: 14.93/ 18.07 GFLOPS | Progress: (16/20) | 12.14 s
[Task 18/25] Current/Best: 3.01/ 18.07 GFLOPS | Progress: (20/20) | 17.97 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.71/ 21.70 GFLOPS | Progress: (4/20) | 3.51 s
[Task 19/25] Current/Best: 6.19/ 21.70 GFLOPS | Progress: (8/20) | 6.55 s
[Task 19/25] Current/Best: 7.65/ 21.70 GFLOPS | Progress: (12/20) | 9.64 s
[Task 19/25] Current/Best: 7.44/ 21.70 GFLOPS | Progress: (16/20) | 12.33 s
[Task 19/25] Current/Best: 12.23/ 21.70 GFLOPS | Progress: (20/20) | 17.81 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.44/ 13.96 GFLOPS | Progress: (4/20) | 3.69 s
[Task 20/25] Current/Best: 13.91/ 13.96 GFLOPS | Progress: (8/20) | 5.66 s
[Task 20/25] Current/Best: 10.26/ 13.96 GFLOPS | Progress: (12/20) | 7.82 s
[Task 20/25] Current/Best: 13.55/ 16.62 GFLOPS | Progress: (16/20) | 10.49 s
[Task 20/25] Current/Best: 16.78/ 18.38 GFLOPS | Progress: (20/20) | 12.57 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 5.37/ 19.38 GFLOPS | Progress: (4/20) | 6.58 s
[Task 21/25] Current/Best: 16.22/ 19.38 GFLOPS | Progress: (8/20) | 7.81 s
[Task 21/25] Current/Best: 13.24/ 19.38 GFLOPS | Progress: (12/20) | 9.39 s
[Task 21/25] Current/Best: 18.86/ 19.38 GFLOPS | Progress: (16/20) | 11.81 s Done.
+
[Task 21/25] Current/Best: 19.10/ 19.38 GFLOPS | Progress: (20/20) | 13.21 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.61/ 12.75 GFLOPS | Progress: (4/20) | 3.12 s
[Task 22/25] Current/Best: 10.19/ 15.48 GFLOPS | Progress: (8/20) | 5.20 s
[Task 22/25] Current/Best: 7.30/ 21.20 GFLOPS | Progress: (12/20) | 7.60 s
[Task 22/25] Current/Best: 10.70/ 21.20 GFLOPS | Progress: (16/20) | 9.34 s
[Task 22/25] Current/Best: 5.11/ 21.20 GFLOPS | Progress: (20/20) | 10.72 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 23.37/ 23.37 GFLOPS | Progress: (4/20) | 3.99 s
[Task 23/25] Current/Best: 7.94/ 23.37 GFLOPS | Progress: (8/20) | 6.68 s
[Task 23/25] Current/Best: 12.03/ 23.37 GFLOPS | Progress: (12/20) | 8.73 s
[Task 23/25] Current/Best: 17.25/ 23.37 GFLOPS | Progress: (16/20) | 12.99 s
[Task 23/25] Current/Best: 10.75/ 23.37 GFLOPS | Progress: (20/20) | 16.68 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.19/ 8.19 GFLOPS | Progress: (4/20) | 12.18 s
[Task 24/25] Current/Best: 3.57/ 10.91 GFLOPS | Progress: (8/20) | 18.26 s
[Task 24/25] Current/Best: 6.16/ 10.91 GFLOPS | Progress: (12/20) | 28.90 s
[Task 24/25] Current/Best: 2.30/ 10.91 GFLOPS | Progress: (16/20) | 32.92 s
[Task 24/25] Current/Best: 9.91/ 10.91 GFLOPS | Progress: (20/20) | 43.37 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 8.03 GFLOPS | Progress: (4/20) | 4.42 s Done.
+
[Task 25/25] Current/Best: 4.24/ 8.03 GFLOPS | Progress: (8/20) | 15.13 s
[Task 25/25] Current/Best: 3.52/ 8.03 GFLOPS | Progress: (12/20) | 16.84 s
[Task 25/25] Current/Best: 9.48/ 9.48 GFLOPS | Progress: (16/20) | 27.12 s
[Task 25/25] Current/Best: 3.45/ 9.48 GFLOPS | Progress: (20/20) | 37.61 s
@@ -674,8 +674,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 429.49089195999477, 'median': 428.73051869999017, 'std': 3.672164925682207}
- unoptimized: {'mean': 509.33978959999877, 'median': 509.0096936000009, 'std': 2.4713246779646143}
+ optimized: {'mean': 406.20252481000534, 'median': 406.1849623500166, 'std': 0.45794469976568325}
+ unoptimized: {'mean': 512.5842140299937, 'median': 513.2335168000054, 'std': 2.1297284277345603}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 46.314 seconds)
+ **Total running time of the script:** ( 10 minutes 48.593 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 7375f1f866..8b0b7364b9 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
- 1.272e-07 secs/op
+ 1.258e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 548d1c5c90..d389154705 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x2303cf60)), stage(b, placeholder(b, 0x2298ed90)), 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, 0xeb82260)), stage(b, placeholder(b, 0x1a7292e0)), 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 67ea3345f1..c0ce83fab4 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
=================
-**14:17.107** total execution time for **tutorial** files:
+**14:14.767** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:46.314 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:48.593 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:20.679 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:29.607 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.787 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:57.996 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.032 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.155 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:32.694 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:21.445 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.778 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.048 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.636 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.757 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.178 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.158 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 9aab89be6f..8688b9f734 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: 0.000008
- naive: 0.000007
+ Numpy running time: 0.000007
+ naive: 0.000008
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000006
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.502419998672849e-06 1.0
- naive 6.6937e-06 0.8922054485331521
- parallel 7.0439000000000004e-06 0.9388837203523717
- vector 2.4597299999999996e-05 3.278582111418871
+ numpy 6.800370001656119e-06 1.0
+ naive 7.876e-06 1.158172275638227
+ parallel 6.0574e-06 0.8907456503873787
+ vector 2.4780599999999998e-05 3.6440076045810867
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018361
+ Numpy running time: 0.017766
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.287395
+ none: 3.200701
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.294193
+ blocking: 0.295959
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.335581
+ vectorization: 0.332753
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.117921
+ loop permutation: 0.112052
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109240
+ array packing: 0.108180
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110468
+ block caching: 0.110148
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146585
+ parallelization: 0.145407
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2873947600999998 1.0
- blocking 0.2941929019 0.08949119998325085
- vectorization 0.33558065569999995 0.10208103382442328
- loop permutation 0.1179210104 0.03587065716330732
- array packing 0.1092396073 0.033229841644170845
- block caching 0.110468246 0.0336035840115045
- parallelization 0.1465854482 0.04459015691670111
+ none 3.2007007586999996 1.0
+ blocking 0.2959594675 0.09246708449564878
+ vectorization 0.33275323990000005 0.10396262099651937
+ loop permutation 0.11205175360000001 0.03500850658888558
+ array packing 0.10817973950000001 0.03379876709997045
+ block caching 0.1101478597 0.03441367000666997
+ parallelization 0.1454066015 0.04542961446950715
diff --git a/docs/commit_hash b/docs/commit_hash
index 12c37dc20d..600364a602 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-647be2b42510bffb3ed78267c19e76263adcac36
+034dc67d032aac3b848e15a87a7fbb5b72a0b909
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 18b9f672bc..5d1d8b5b82 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 22.704 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.345 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 ba765a2ae8..193696ef31 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 970ms/step
+1/1 [==============================] - 1s 942ms/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 d7d1e8f36c..306779b15b 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.zipf3c04b29-7dab-4be3-aa9e-a75f69ae701c 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.zip15cabb9c-945d-461e-a62b-cdb0c4474b5d 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 75511eccbe..1f0c7d817a 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,13 +448,12 @@ 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, 57.0MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 68.0MB/s]
- 55%|#####4 | 22.6M/41.5M [00:00<00:00, 67.0MB/s]
- 70%|####### | 29.1M/41.5M [00:00<00:00, 60.6MB/s]
- 84%|########4 | 35.0M/41.5M [00:00<00:00, 52.0MB/s]
- 98%|#########8| 40.8M/41.5M [00:00<00:00, 54.6MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 58.1MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 71.2MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 61.7MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 63.4MB/s]
+ 69%|######8 | 28.5M/41.5M [00:00<00:00, 57.6MB/s]
+ 82%|########2 | 34.0M/41.5M [00:00<00:00, 47.8MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 57.5MB/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 e983e210e8..17ab19d881 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,13 +431,12 @@ 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]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 46.9MB/s]
- 32%|###2 | 14.3M/44.7M [00:00<00:00, 46.4MB/s]
- 42%|####1 | 18.7M/44.7M [00:00<00:00, 44.9MB/s]
- 54%|#####3 | 24.0M/44.7M [00:00<00:00, 40.6MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 44.0MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 50.6MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 49.8MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 78.3MB/s]
+ 40%|###9 | 17.7M/44.7M [00:00<00:00, 91.5MB/s]
+ 59%|#####9 | 26.4M/44.7M [00:00<00:00, 55.8MB/s]
+ 74%|#######3 | 32.8M/44.7M [00:00<00:00, 50.3MB/s]
+ 90%|########9 | 40.0M/44.7M [00:00<00:00, 52.2MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 58.0MB/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 1804a268b0..36e0cfdb8a 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 11.496 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.066 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 b49cb27aae..2f3f77cd2b 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>06:01.124</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:41.107</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_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>01:22.704</p></td>
+<td><p>01:11.345</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:11.496</p></td>
+<td><p>01:10.066</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>00:47.587</p></td>
+<td><p>00:44.957</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>00:32.946</p></td>
+<td><p>00:32.583</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>00:29.628</p></td>
+<td><p>00:29.915</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>00:26.945</p></td>
+<td><p>00:26.073</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>00:25.545</p></td>
+<td><p>00:24.966</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>00:23.317</p></td>
+<td><p>00:21.625</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>00:18.517</p></td>
+<td><p>00:17.182</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>00:02.440</p></td>
+<td><p>00:02.395</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 9787491dbd..7e1129c26a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2278 16.2067 16.4092 16.0635 0.1238
+ 15.5598 15.5219 15.8895 15.4592 0.1152
</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 b8a2ae6193..7dbc78624d 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 +453,33 @@ 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, 75.1MB/s]
- 9%|8 | 15.2M/170M [00:00<00:02, 74.2MB/s]
- 13%|#3 | 22.2M/170M [00:00<00:02, 62.2MB/s]
- 17%|#6 | 28.3M/170M [00:00<00:02, 57.6MB/s]
- 20%|#9 | 33.9M/170M [00:00<00:02, 52.6MB/s]
- 24%|##3 | 40.4M/170M [00:00<00:02, 57.0MB/s]
- 28%|##7 | 47.2M/170M [00:00<00:02, 61.1MB/s]
- 31%|###1 | 53.1M/170M [00:00<00:02, 51.4MB/s]
- 36%|###6 | 61.4M/170M [00:01<00:01, 60.5MB/s]
- 40%|###9 | 67.6M/170M [00:01<00:02, 52.9MB/s]
- 43%|####2 | 73.0M/170M [00:01<00:01, 51.7MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 51.1MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 45.9MB/s]
- 56%|#####5 | 94.3M/170M [00:01<00:01, 47.5MB/s]
- 59%|#####8 | 100M/170M [00:01<00:01, 50.1MB/s]
- 63%|######3 | 108M/170M [00:02<00:01, 57.2MB/s]
- 67%|######6 | 113M/170M [00:02<00:01, 51.6MB/s]
- 71%|####### | 120M/170M [00:02<00:00, 54.8MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 60.1MB/s]
- 80%|######## | 136M/170M [00:02<00:00, 57.0MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 63.3MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 60.2MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 55.4MB/s]
- 99%|#########8| 168M/170M [00:03<00:00, 57.8MB/s]
-100%|##########| 170M/170M [00:03<00:00, 56.3MB/s]
+ 4%|3 | 6.30M/170M [00:00<00:02, 60.3MB/s]
+ 7%|7 | 12.1M/170M [00:00<00:03, 49.6MB/s]
+ 10%|9 | 16.9M/170M [00:00<00:03, 47.6MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:03, 50.5MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:02, 57.4MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:02, 59.7MB/s]
+ 27%|##7 | 46.3M/170M [00:00<00:02, 59.8MB/s]
+ 31%|### | 52.0M/170M [00:00<00:02, 56.7MB/s]
+ 36%|###5 | 60.3M/170M [00:01<00:01, 65.0MB/s]
+ 39%|###9 | 66.7M/170M [00:01<00:01, 63.5MB/s]
+ 43%|####2 | 72.8M/170M [00:01<00:01, 63.6MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 65.5MB/s]
+ 51%|##### | 86.3M/170M [00:01<00:01, 59.0MB/s]
+ 54%|#####4 | 92.1M/170M [00:01<00:01, 51.4MB/s]
+ 57%|#####7 | 97.2M/170M [00:01<00:01, 49.3MB/s]
+ 61%|######1 | 104M/170M [00:01<00:01, 48.2MB/s]
+ 66%|######5 | 112M/170M [00:02<00:01, 55.2MB/s]
+ 71%|####### | 120M/170M [00:02<00:00, 55.2MB/s]
+ 75%|#######5 | 128M/170M [00:02<00:00, 53.5MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 55.9MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 53.5MB/s]
+ 88%|########8 | 150M/170M [00:02<00:00, 50.9MB/s]
+ 91%|#########1| 155M/170M [00:02<00:00, 47.5MB/s]
+ 94%|#########4| 160M/170M [00:03<00:00, 41.3MB/s]
+ 96%|#########6| 164M/170M [00:03<00:00, 38.2MB/s]
+ 99%|#########8| 168M/170M [00:03<00:00, 36.6MB/s]
+100%|##########| 170M/170M [00:03<00:00, 51.8MB/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 +577,7 @@ 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 13.965 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 8.345 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 7b41d785d8..1e3920b2eb 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ 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]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 58.0MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 74.0MB/s]
+ 75%|#######5 | 10.2M/13.6M [00:00<00:00, 107MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 127MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ 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)
- 88.9665 88.8580 94.4067 88.7508 0.5745
+ 90.1390 90.0956 91.8675 89.9643 0.2382
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ 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 5.160 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.408 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 51d3c8584d..7fb57bad20 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)
- 118.7686 118.7043 119.7815 118.0459 0.3485
+ 117.5577 117.1141 120.8395 115.9301 1.1803
</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 25.879 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 21.058 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 febcb8d203..5bc04d41f5 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 35.353 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.639 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 ef26a90cdd..2030a32a90 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,23 +462,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6171/132723 [00:00<00:02, 61701.09KB/s]
- 11%|#1 | 14843/132723 [00:00<00:01, 76410.30KB/s]
- 18%|#7 | 23515/132723 [00:00<00:01, 81114.04KB/s]
- 24%|##4 | 32142/132723 [00:00<00:01, 83145.91KB/s]
- 31%|### | 40831/132723 [00:00<00:01, 84492.43KB/s]
- 37%|###7 | 49396/132723 [00:00<00:01, 82871.36KB/s]
- 43%|####3 | 57691/132723 [00:00<00:01, 73223.98KB/s]
- 49%|####9 | 65197/132723 [00:00<00:00, 70633.56KB/s]
- 55%|#####4 | 72386/132723 [00:00<00:00, 66933.18KB/s]
- 60%|###### | 79980/132723 [00:01<00:00, 69418.53KB/s]
- 66%|######5 | 87020/132723 [00:01<00:00, 63332.39KB/s]
- 72%|#######1 | 95348/132723 [00:01<00:00, 68684.41KB/s]
- 78%|#######8 | 103819/132723 [00:01<00:00, 73125.44KB/s]
- 85%|########4 | 112394/132723 [00:01<00:00, 76705.70KB/s]
- 91%|#########1| 120976/132723 [00:01<00:00, 79332.85KB/s]
- 98%|#########7| 129574/132723 [00:01<00:00, 81269.80KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75466.07KB/s]
+ 4%|4 | 5510/132723 [00:00<00:02, 55095.72KB/s]
+ 11%|# | 14232/132723 [00:00<00:01, 73977.89KB/s]
+ 16%|#6 | 21865/132723 [00:00<00:01, 75046.43KB/s]
+ 23%|##3 | 30549/132723 [00:00<00:01, 79697.24KB/s]
+ 29%|##9 | 39045/132723 [00:00<00:01, 81592.25KB/s]
+ 36%|###5 | 47677/132723 [00:00<00:01, 83195.45KB/s]
+ 42%|####2 | 56298/132723 [00:00<00:00, 84178.42KB/s]
+ 49%|####8 | 64996/132723 [00:00<00:00, 85069.03KB/s]
+ 56%|#####5 | 73711/132723 [00:00<00:00, 85718.15KB/s]
+ 62%|######2 | 82429/132723 [00:01<00:00, 86165.77KB/s]
+ 69%|######8 | 91116/132723 [00:01<00:00, 86379.11KB/s]
+ 75%|#######5 | 99838/132723 [00:01<00:00, 86631.72KB/s]
+ 82%|########1 | 108510/132723 [00:01<00:00, 86656.67KB/s]
+ 88%|########8 | 117176/132723 [00:01<00:00, 86574.79KB/s]
+ 95%|#########4| 125902/132723 [00:01<00:00, 86773.86KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83993.06KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +516,7 @@ 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 0.177 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 56.170 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 ff98c51623..d2b534916b 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>12:47.465</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:28.240</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>03:13.965</p></td>
+<td><p>03:08.345</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>03:00.177</p></td>
+<td><p>02:56.170</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>02:25.879</p></td>
+<td><p>02:21.058</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>01:35.353</p></td>
+<td><p>01:34.639</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>01:05.160</p></td>
+<td><p>01:04.408</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:36.150</p></td>
+<td><p>00:34.996</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.920</p></td>
+<td><p>00:24.542</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.856</p></td>
+<td><p>00:24.076</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 92f9040d6f..61f2a280c1 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.zipeba92fe9-b7ba-4a30-b928-654b4429714f 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.zip3d748125-a20a-47a1-8324-db47c1b3e1c6 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 eb45a2e635..7c6a069355 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>00:46.492</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:47.737</strong> total execution time for <strong>how_to_extend_tvm</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="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>00:43.101</p></td>
+<td><p>00:44.332</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>00:02.370</p></td>
+<td><p>00:02.376</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>00:01.014</p></td>
+<td><p>00:01.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 3e9ea43439..cb6b84bda0 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: 7006us [7006us] (46.58%; 46.58%)
-FoldScaleAxis: 8036us [6us] (53.42%; 53.42%)
- FoldConstant: 8029us [1658us] (53.38%; 99.92%)
- InferType: 6371us [6371us] (42.36%; 79.35%)
+InferType: 7121us [7121us] (46.33%; 46.33%)
+FoldScaleAxis: 8250us [6us] (53.67%; 53.67%)
+ FoldConstant: 8244us [1672us] (53.63%; 99.93%)
+ InferType: 6572us [6572us] (42.75%; 79.72%)
</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: 6485us [6485us] (44.96%; 44.96%)
-FoldScaleAxis: 7939us [5us] (55.04%; 55.04%)
- FoldConstant: 7934us [1631us] (55.01%; 99.94%)
- InferType: 6303us [6303us] (43.70%; 79.45%)
+InferType: 6615us [6615us] (45.04%; 45.04%)
+FoldScaleAxis: 8072us [5us] (54.96%; 54.96%)
+ FoldConstant: 8067us [1650us] (54.93%; 99.94%)
+ InferType: 6417us [6417us] (43.69%; 79.55%)
</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 d9be319f65..09be5847cc 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: 48.046081 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.112255 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 d01c43d773..77f942c69d 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -916,7 +916,7 @@ 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: 13.374019 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.913606 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 80dd804f3b..47dbaf89b7 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: 0.018808
-Baseline: 3.429418
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018163
+Baseline: 3.201460
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -535,7 +535,7 @@ 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: 0.314154
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.298053
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -602,7 +602,7 @@ 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: 0.345004
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.328097
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -663,7 +663,7 @@ 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: 0.121400
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.112942
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -746,7 +746,7 @@ 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: 0.109632
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108599
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -832,7 +832,7 @@ 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: 0.109297
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110638
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -922,7 +922,7 @@ 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: 0.144817
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146956
</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 88664f2658..39828b7d8b 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>00:35.254</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.181</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>00:32.611</p></td>
+<td><p>00:31.468</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>00:01.503</p></td>
+<td><p>00:01.538</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>00:01.140</p></td>
+<td><p>00:01.175</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 616462b429..e70579716b 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>09:19.956</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:12.439</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -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>05:41.167</p></td>
+<td><p>05:37.658</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>01:33.349</p></td>
+<td><p>01:31.191</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>01:03.566</p></td>
+<td><p>01:02.194</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>00:38.473</p></td>
+<td><p>00:38.904</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>00:12.101</p></td>
+<td><p>00:11.659</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>00:11.299</p></td>
+<td><p>00:10.834</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 fdbee18a7a..34826d3dbb 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
@@ -506,581 +506,319 @@ cooperative fetching, unrolling and operator fusion.</p>
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
- let cse_var_2: int32 = (rc.outer.outer*196)
- let cse_var_1: int32 = (rc.outer.outer*36)
+ for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_1: int32 = (rc.outer.outer*1568)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[(threadIdx.x_1*2)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*2), 81)) && (floormod((threadIdx.x_1*2), 81) < 72)) && (1 <= floormod((threadIdx.x_1*2), 9))) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 81)*49)) + (floordiv(floormod((threadIdx.x_1*2), 81), 9)*7)) + floormod((threadIdx.x_1*2), 9)) - 8) [...]
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 1), 81)) && (floormod(((threadIdx.x_1*2) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 9))) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_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" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else((((threadIdx.x_1 < 48) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 728), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 30), 81)) && (floormod((threadIdx.x_1 + 30), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 840), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 30), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 61), 81)) && (floormod((threadIdx.x_1 + 61), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 952), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 61), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1064)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 2), 9)) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1064), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1288)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 73), 81)) && (floormod((threadIdx.x_1 + 73), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1288), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 73), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1344), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1400)] = @tir.if_then_else((((threadIdx.x_1 < 49) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1400), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1456), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1512)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 6), 9)) && (floormod((threadIdx.x_1 + 54), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1512), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 6), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1624)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1624), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 60), 81)) && (floormod((threadIdx.x_1 + 60), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1680), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1736)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 35), 81)) && (floormod((threadIdx.x_1 + 35), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1736), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 35), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 1), 9)) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1792), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1848)] = @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[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1848), 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" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 41), 81)) && (floormod((threadIdx.x_1 + 41), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1904), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 41), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 7), 9)) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2016), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2072)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 47), 81)) && (floormod((threadIdx.x_1 + 47), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2072), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 47), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else((((threadIdx.x_1 < 50) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2128), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 22), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2184)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 78), 81)) && (floormod((threadIdx.x_1 + 78), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2184), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 78), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2240), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2296)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 28), 81)) && (floormod((threadIdx.x_1 + 28), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2296), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 28), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2408)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2408), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @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[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2464), 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" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 2520)] = @tir.if_then_else(((1 <= floormod(threadIdx.x_1, 9)) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2520), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 1)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 2576), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- pad_temp.shared_1[((threadIdx.x_1*2) + 112)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 31), 81)) && (floormod(((threadIdx.x_1*2) + 31), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 4), 9))) && (floormod(((threadIdx.x_1*2) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 112), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 31), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 113)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 32), 81)) && (floormod(((threadIdx.x_1*2) + 32), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 5), 9))) && (floormod(((threadIdx.x_1*2) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 113), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 32), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 224)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 62), 81)) && (floormod(((threadIdx.x_1*2) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 8), 9))) && (floormod(((threadIdx.x_1*2) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 224), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 62), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 8), 9)) - 8)], 0f32, dtype [...]
- }
- if @tir.likely((threadIdx.x_1 < 50), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 225)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*2), 9) + 7), 9)) && (floormod(((threadIdx.x_1*2) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*2), 9))) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 225), 81)*49)) + (floormod((floordiv((threadIdx.x_1*2), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*2), 9)) - 8)], 0f32, dtype=float32)
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48))] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*16)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fuse [...]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 1)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*16)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 2)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*16)), 96), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 4)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 5)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 1), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 7)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 8)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 2), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 10)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 11)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 1), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 13)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 14)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 4), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 16)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 17)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 5), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 19)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 20)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 2), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 22)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 23)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 7), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 8), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 25)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 8), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 26)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 8), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 3), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 28)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 3), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 29)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 3), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 10), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 31)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 10), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 32)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 10), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 33)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 11), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 34)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 11), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 35)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 11), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 36)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 4), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 37)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 4), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 38)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 4), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 39)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 13), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 40)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 13), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 41)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 13), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 42)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 14), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 43)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 14), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 44)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)) + 14), 96), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 45)] = kernel[(((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 5), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 46)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 5), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ }
+ if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 8)) < 12), dtype=bool) {
+ kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*48)) + 47)] = kernel[((((((blockIdx.x*73728) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_2, 2)), 3)*4608)) + (rc.outer.outer*288)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*16)), 3) + 5), 32)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ }
}
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 24), 36), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 36)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 36), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 12), 36), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 36), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 36), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 36)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 36)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 36)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 36), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ for (rc.outer.inner: int32, 0, 2) {
+ for (ry.outer.inner: int32, 0, 3) {
+ for (rx.outer.inner: int32, 0, 3) {
+ for (xx.outer.inner: int32, 0, 7) {
+ let cse_var_2: int32 = (xx.outer.inner + 7)
+ {
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[(((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 162)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 243)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 324)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 405)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 486)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 567)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 648)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 648)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 729)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 729)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 810)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 810)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 891)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 891)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 972)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 972)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1053)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1053)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1134)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1134)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1215)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[cse_var_2] = (conv2d_nchw_1[cse_var_2] + (pad_temp.shared_1[((((((rc.outer.inner*1296) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + rx.outer.inner) + 1215)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*576) + (rc.outer.inner*144)) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ }
+ }
+ }
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
}
}
for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -1117,7 +855,7 @@ 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: 0.208 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.261 ms
</pre></div>
</div>
</div>
@@ -1146,8 +884,8 @@ 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=2)
+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=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
@@ -1155,15 +893,15 @@ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+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=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
@@ -1174,9 +912,9 @@ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1193,16 +931,16 @@ 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=1)
+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=48)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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=2)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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:
@@ -1222,561 +960,265 @@ CUDA source code:
#endif
extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[324];
- __shared__ float kernel_shared[576];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = (((((9 <= ((((int)threadIdx.x) * 2) % 81)) && (((((int)threadIdx.x) * 2) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) * 2) / 81) * 49)) + ((((((int)threadIdx.x) * 2) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((((9 <= (((((int)threadIdx.x) * 2) + 1) % 81)) && ((((((int)threadIdx.x) * 2) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 112)] = (((((9 <= (((((int)threadIdx.x) * 2) + 31) % 81)) && ((((((int)threadIdx.x) * 2) + 31) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 4) % 9))) && ((((((int)threadIdx.x) * 2) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 112) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 31) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 113)] = (((((9 <= (((((int)threadIdx.x) * 2) + 32) % 81)) && ((((((int)threadIdx.x) * 2) + 32) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 113) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 32) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 224)] = (((((9 <= (((((int)threadIdx.x) * 2) + 62) % 81)) && ((((((int)threadIdx.x) * 2) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 224) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 50) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 225)] = (((((1 <= ((((((int)threadIdx.x) * 2) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 2) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((((int)threadIdx.x) * 2) + 225) / 81) * 49)) + (((((((int)threadIdx.x) * 2) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 20) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 4) % 36))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 24) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 8) % 36))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 28) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 12) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 32) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 16) % 36) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) % 36)) + 64512)];
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = ((((((int)threadIdx.x) < 48) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + (((((int)threadIdx.x) + 24) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 728)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 728) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 840)] = (((((9 <= ((((int)threadIdx.x) + 30) % 81)) && (((((int)threadIdx.x) + 30) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 840) / 81) * 49)) + ((((((int)threadIdx.x) + 30) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = ((((4 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + (((((int)threadIdx.x) + 5) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 952)] = (((((9 <= ((((int)threadIdx.x) + 61) % 81)) && (((((int)threadIdx.x) + 61) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 952) / 81) * 49)) + ((((((int)threadIdx.x) + 61) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1064)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1064) / 81) * 49)) + (((((int)threadIdx.x) + 11) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1288)] = (((((9 <= ((((int)threadIdx.x) + 73) % 81)) && (((((int)threadIdx.x) + 73) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1288) / 81) * 49)) + ((((((int)threadIdx.x) + 73) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1400)] = ((((((int)threadIdx.x) < 49) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1400) / 81) * 49)) + (((((int)threadIdx.x) + 23) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1512)] = (((((1 <= (((((int)threadIdx.x) / 9) + 6) % 9)) && (((((int)threadIdx.x) + 54) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1512) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 6) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1624)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1624) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((9 <= ((((int)threadIdx.x) + 60) % 81)) && (((((int)threadIdx.x) + 60) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 81) * 49)) + ((((((int)threadIdx.x) + 60) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1736)] = (((((9 <= ((((int)threadIdx.x) + 35) % 81)) && (((((int)threadIdx.x) + 35) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1736) / 81) * 49)) + ((((((int)threadIdx.x) + 35) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + (((((int)threadIdx.x) + 10) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1848)] = (((((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 * 1568) + (((((int)threadIdx.x) + 1848) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((9 <= ((((int)threadIdx.x) + 41) % 81)) && (((((int)threadIdx.x) + 41) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 81) * 49)) + ((((((int)threadIdx.x) + 41) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((1 <= ((((int)threadIdx.x) + 7) % 9)) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + (((((int)threadIdx.x) + 16) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2072)] = (((((9 <= ((((int)threadIdx.x) + 47) % 81)) && (((((int)threadIdx.x) + 47) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2072) / 81) * 49)) + ((((((int)threadIdx.x) + 47) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = ((((((int)threadIdx.x) < 50) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2128) / 81) * 49)) + (((((int)threadIdx.x) + 22) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2184)] = (((((9 <= ((((int)threadIdx.x) + 78) % 81)) && (((((int)threadIdx.x) + 78) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2184) / 81) * 49)) + ((((((int)threadIdx.x) + 78) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2296)] = (((((9 <= ((((int)threadIdx.x) + 28) % 81)) && (((((int)threadIdx.x) + 28) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2296) / 81) * 49)) + ((((((int)threadIdx.x) + 28) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((6 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + (((((int)threadIdx.x) + 3) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2408)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2408) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((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 * 1568) + (((((int)threadIdx.x) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2520)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2520) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 1)] : 0.000000e+00f);
if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) + 20) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2576) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48))] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 16)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 16)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 16)) % 96) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 5)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 1) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 7)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 2) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 10)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 11)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 1) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 13)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 14)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 4) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 16)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 17)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 5) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 19)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 20)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 2) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 22)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 23)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 7) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 8) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 25)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 8) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 26)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 8) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 3) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 28)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 3) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 29)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 3) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 10) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 31)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 10) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 32)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 10) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 33)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 11) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 34)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 11) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 35)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 11) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 36)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 4) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 37)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 4) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 38)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 4) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 39)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 13) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 40)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 13) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 41)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 13) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 1) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 42)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 14) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3) [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 43)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 14) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 44)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) + 14) % 96) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) + 2) % 3 [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 45)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 5) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 46)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 5) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 3)) < 12) {
+ kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 48)) + 47)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 1)) / 3) * 4608)) + (rc_outer_outer * 288)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 16)) / 3) + 5) & 31) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ }
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[(((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 162)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 243)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 324)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 405)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 486)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 567)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 648)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 648)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 729)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 729)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 810)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 810)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 891)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 891)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 972)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 972)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1053)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1053)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1134)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1134)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1215)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[(xx_outer_inner + 7)] = (conv2d_nchw[(xx_outer_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 1296) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + rx_outer_inner) + 1215)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 576) + (rc_outer_inner * 144)) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ }
+ }
+ }
+ }
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -1813,7 +1255,7 @@ 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 41.167 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 37.658 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 d5ff8b2359..9ed0774e76 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)
- 8.2442 8.2451 8.2605 8.2271 0.0136
+ 8.1684 8.1745 8.1780 8.1528 0.0111
</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 3.566 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.194 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 f17014b41f..21928f2012 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)
- 761.5858 761.5612 761.9018 761.2943 0.2486
+ 749.1891 749.6458 751.5422 746.3793 2.1323
</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 33.349 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.191 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 f373b44d78..a80e54a08d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,59 +632,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 16)
- let cse_var_1: int32 = (i.outer.inner*8)
- {
- compute_5: Buffer(compute_4, float32, [128], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (cse_var_1 + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_4: int32 = (cse_var_1 + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_5: int32 = (cse_var_1 + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_6: int32 = (cse_var_1 + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_7: int32 = (cse_var_1 + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_8: int32 = (cse_var_1 + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_9: int32 = (cse_var_1 + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + floormod(i0.outer.i1.outer.fused, 16))]*max(placeholder[(((i.outer.inner*2048) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [256], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_10: int32 = ((i0.inner*512) + i0.outer.i1.outer.fused)
- compute[cse_var_10] = max((compute_5[i0.inner] + placeholder_4[cse_var_10]), 0f32)
+ for (i0.inner: int32, 0, 8) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -722,7 +693,7 @@ 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: 4.086 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.599 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 dfc928664b..d990bc181e 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>00:42.994</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:40.308</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:42.960</p></td>
+<td><p>00:40.272</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.019</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
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 0ddb5c615a..5f79784dad 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 6.15/6.15 result: MeasureResult(costs=(0.03765760025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.275269031524658, timestamp=1668492496.9377825) [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,626203
-No: 2 GFLOPS: 0.00/6.15 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -690,10 +689,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2967214
-No: 3 GFLOPS: 7.94/7.94 result: MeasureResult(costs=(0.029165311750000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8207025527954102, timestamp=1668492498.5616288) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2087599
-No: 4 GFLOPS: 178.18/178.18 result: MeasureResult(costs=(0.001299231987012987,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7496528625488281, timestamp=1668492500.1057882) [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4261770
-No: 5 GFLOPS: 0.00/178.18 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9666825
+No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -815,163 +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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8350362
-No: 6 GFLOPS: 205.86/205.86 result: MeasureResult(costs=(0.0011245512342342343,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.502927303314209, timestamp=1668492504.893299) [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6076876
-No: 7 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007ff6a869dfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1978908
-No: 8 GFLOPS: 115.47/205.86 result: MeasureResult(costs=(0.0020049101200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.099451780319214, timestamp=1668492510.9292245) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8236475
-No: 9 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1217071
+No: 3 GFLOPS: 31.16/31.16 result: MeasureResult(costs=(0.007428685857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8253495693206787, timestamp=1668512663.8954246) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1051435
+No: 4 GFLOPS: 0.00/31.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1093,8 +936,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8032009
-No: 10 GFLOPS: 0.00/205.86 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, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10044682
+No: 5 GFLOPS: 8.87/31.16 result: MeasureResult(costs=(0.026085815249999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.142474889755249, timestamp=1668512673.1282887) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8794587
+No: 6 GFLOPS: 0.00/31.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1216,8 +1060,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7356517
-No: 11 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1715554
+No: 7 GFLOPS: 0.00/31.16 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1339,8 +1183,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5763691
-No: 12 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9211582
+No: 8 GFLOPS: 212.05/212.05 result: MeasureResult(costs=(0.0010917095714285713,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5799691677093506, timestamp=1668512674.066223) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1951455
+No: 9 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1462,9 +1307,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4804238
-No: 13 GFLOPS: 152.73/205.86 result: MeasureResult(costs=(0.0015157305000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.202910900115967, timestamp=1668492516.5718539) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7464226
-No: 14 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,765924
+No: 10 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1586,8 +1430,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4857815
-No: 15 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7085674
+No: 11 GFLOPS: 4.58/212.05 result: MeasureResult(costs=(0.05049862275,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4923033714294434, timestamp=1668512675.7578967) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,996160
+No: 12 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1709,8 +1554,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1960765
-No: 16 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1570957
+No: 13 GFLOPS: 67.57/212.05 result: MeasureResult(costs=(0.0034263342571428574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5604088306427002, timestamp=1668512679.5054412) [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5273534
+No: 14 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1832,8 +1678,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,901418
-No: 17 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1151557
+No: 15 GFLOPS: 106.35/212.05 result: MeasureResult(costs=(0.002176714347826087,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.306579351425171, timestamp=1668512680.1356115) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2451920
+No: 16 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -1921,7 +1768,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f9583403fa2
+ 12: 0x00007fdf4c19afa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -1985,8 +1832,8 @@ Traceback (most recent call last):
22: _PyEval_EvalFrameDefault
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8340166
-No: 18 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+ 19: _PyFunction_FastCall [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,974519
+No: 17 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2108,8 +1955,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3153633
-No: 19 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8493371
+No: 18 GFLOPS: 0.00/212.05 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2231,8 +2078,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,756836
-No: 20 GFLOPS: 0.00/205.86 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10056444
+No: 19 GFLOPS: 341.57/341.57 result: MeasureResult(costs=(0.0006777660743243244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9776229858398438, timestamp=1668512685.8448713) [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4108374
+No: 20 GFLOPS: 0.00/341.57 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2354,7 +2202,7 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6791120
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10170862
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2393,9 +2241,9 @@ 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, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6076876
+[('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4108374
Finish loading 20 records
-Time cost of this operator: 0.001368
+Time cost of this operator: 0.001069
</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 bfd216f53f..71a0a47d70 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -596,10 +596,10 @@ 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 314.1 98.58 (1, 2, 10, 10, 3) 2 1 [314.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.559 1.117 (1, 6, 10, 10) 1 1 [3.559]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.303 (1, 1, 10, 10, 3) 1 1 [0.964]
-Total_time - 318.623 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.5 98.731 (1, 2, 10, 10, 3) 2 1 [311.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.957 (1, 6, 10, 10) 1 1 [3.021]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.312 (1, 1, 10, 10, 3) 1 1 [0.984]
+Total_time - 315.505 - - - - -
</pre></div>
</div>
</div>
@@ -650,10 +650,10 @@ 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 103.3 97.531 (1, 6, 10, 10, 1) 2 1 [103.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.774 1.675 (1, 6, 10, 10) 1 1 [1.774]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.84 0.793 (1, 3, 10, 10, 1) 1 1 [0.84]
-Total_time - 105.915 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 101.3 97.366 (1, 6, 10, 10, 1) 2 1 [101.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.696 (1, 6, 10, 10) 1 1 [1.765]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.938 (1, 1, 10, 10, 3) 1 1 [0.976]
+Total_time - 104.041 - - - - -
</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 235c3e305d..bd3ddd36fb 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,7 +440,8 @@ 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, 48.9MB/s]
+ 29%|##9 | 1.00M/3.42M [00:00<00:00, 10.4MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 26.0MB/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 +565,7 @@ 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 3.137 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.016 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 0af53eb892..a5b23890e7 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/tmpv9m_xlv4/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmppttw5wrc/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], [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/tmpv9m_xlv4/images/target contains 8144 images
-/tmp/tmpv9m_xlv4/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmppttw5wrc/images/target contains 8144 images
+/tmp/tmppttw5wrc/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: 0.2101 - accuracy: 0.9251 - val_loss: 0.1412 - val_accuracy: 0.9592 - 47s/epoch - 144ms/step
+328/328 - 46s - loss: 0.2159 - accuracy: 0.9249 - val_loss: 0.1130 - val_accuracy: 0.9585 - 46s/epoch - 141ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0943 - accuracy: 0.9650 - val_loss: 0.0996 - val_accuracy: 0.9690 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0959 - accuracy: 0.9662 - val_loss: 0.1393 - val_accuracy: 0.9498 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0668 - accuracy: 0.9759 - val_loss: 0.1160 - val_accuracy: 0.9690 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0740 - accuracy: 0.9727 - val_loss: 0.1125 - val_accuracy: 0.9626 - 43s/epoch - 130ms/step
-<keras.callbacks.History object at 0x7fd545ade990>
+<keras.callbacks.History object at 0x7f7752820f90>
</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 45.497 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 31.174 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 4092f8816e..4c7a59bbf3 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>06:51.087</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:32.444</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>04:45.497</p></td>
+<td><p>04:31.174</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>01:03.137</p></td>
+<td><p>01:01.016</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>00:50.145</p></td>
+<td><p>00:48.255</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>00:08.503</p></td>
+<td><p>00:08.263</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>00:03.803</p></td>
+<td><p>00:03.734</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 a261ac1782..433f37d7b3 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>00:42.112</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.186</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>00:31.962</p></td>
+<td><p>00:31.569</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>00:08.729</p></td>
+<td><p>00:10.075</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>00:01.414</p></td>
+<td><p>00:01.536</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 350f8942c7..5f31066500 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 0x7fd5a0aca3b0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f7752aa3b00>
</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 eda736aa55..ee6e43b13e 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>00:08.082</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.756</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</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>00:05.699</p></td>
+<td><p>00:02.357</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>00:01.046</p></td>
+<td><p>00:01.053</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>00:00.569</p></td>
+<td><p>00:00.577</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>00:00.554</p></td>
+<td><p>00:00.561</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>00:00.116</p></td>
+<td><p>00:00.113</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>00:00.049</p></td>
+<td><p>00:00.048</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>
@@ -377,7 +377,7 @@
<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>00:00.019</p></td>
+<td><p>00:00.018</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 496324edc3..42271346db 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -590,7 +590,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpaz957g8n/input0.cc'\nsource_filename = \"/tmp/tmpaz957g8n/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/tmpokfjtees/input0.cc'\nsource_filename = \"/tmp/tmpokfjtees/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 09681f659a..1cc6259bee 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/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index c52bc0e9da..f68219d86d 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/647be2b42/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 6cc24198bb..806144faf8 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/647be2b42/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 6ee6c9ca13..0f11cbe94c 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/647be2b42/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 72bbdc50d2..6573c33157 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/647be2b42/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 b9e204a5ab..deb01618bf 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/647be2b42/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 ccbef805f8..ccb0005418 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/647be2b42/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 ca3befd551..fa6196e0a4 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/647be2b42/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 839ff9220a..97bf29677d 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/647be2b42/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 983a39773e..052f01bf76 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/647be2b42/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 04aaf7aeb3..85cd5176e5 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/647be2b42/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 726f11662b..709ba4baee 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/647be2b42/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 4364c5bc93..478feabedd 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/647be2b42/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 00d1e954da..edc7d68033 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/647be2b42/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 58d8ee7bd9..e33786fecb 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/647be2b42/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 51306ae58a..68e7779abb 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/647be2b42/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 2952c0f5a3..989b0bd3f1 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/647be2b42/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 9febeae1c5..8d92a82a60 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/647be2b42/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 aa9a3725ae..0e32d22c1f 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/647be2b42/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 f56228e14f..07314052b3 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/647be2b42/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 0baf0513a4..b598acbcae 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/647be2b42/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 d9e291f0d1..54c0c12dd5 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/647be2b42/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 d71cb60c63..df8020a811 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/647be2b42/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 a83ee57295..1c46130739 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/647be2b42/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 fc3155d379..28d4b39ac7 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/647be2b42/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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/647be2b42/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/034dc67d0/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 509a259cb2..40b94a219d 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 9a2bde20d8..3bffceea58 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>00:26.434</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.414</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</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>00:26.428</p></td>
+<td><p>00:26.408</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>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 26b509b70c..8c483ae964 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 28.76s!
+resnet18_v1 inference graph built in 28.42s!
</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 4fd43bc91c..1464c0bbdc 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 19.78s!
+yolov3-tiny inference graph built in 19.45s!
</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 972fbf321d..ef942b0bfc 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>01:40.714</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:40.545</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>00:52.093</p></td>
+<td><p>00:52.041</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>00:48.621</p></td>
+<td><p>00:48.504</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 e74a187f20..cae07b898b 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>00:03.142</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.226</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>00:02.695</p></td>
+<td><p>00:02.763</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>00:00.447</p></td>
+<td><p>00:00.463</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 5753f8d85a..fabab97b66 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>00:00.792</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.824</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>00:00.425</p></td>
+<td><p>00:00.438</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>00:00.367</p></td>
+<td><p>00:00.386</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 89bdb2f441..b4d56f4c41 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,6 +491,9 @@ 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>
@@ -578,7 +581,7 @@ 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: 94.465 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 99.230 ms
</pre></div>
</div>
</div>
@@ -652,7 +655,7 @@ 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 20.679 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.607 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 58c7244bef..9ba4c8f045 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: 0.94/0.94 result: MeasureResult(costs=(0.28453201939999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.70817494392395, timestamp=1668491114.0931864) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
-No: 2 GFLOPS: 12.68/12.68 result: MeasureResult(costs=(0.0211742646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5676043033599854, timestamp=1668491115.3570225) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
-No: 3 GFLOPS: 14.74/14.74 result: MeasureResult(costs=(0.01821234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7354567050933838, timestamp=1668491115.8122365) [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
-No: 4 GFLOPS: 3.15/14.74 result: MeasureResult(costs=(0.08535189400000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5294511318206787, timestamp=1668491118.093534) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
-No: 5 GFLOPS: 1.15/14.74 result: MeasureResult(costs=(0.23308930180000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9469738006591797, timestamp=1668491122.1903) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
-No: 6 GFLOPS: 10.84/14.74 result: MeasureResult(costs=(0.0247700522,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5869479179382324, timestamp=1668491122.7561338) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
-No: 7 GFLOPS: 11.45/14.74 result: MeasureResult(costs=(0.0234400864,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5295507907867432, timestamp=1668491124.04584) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
-No: 8 GFLOPS: 0.50/14.74 result: MeasureResult(costs=(0.5341811477999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.7483389377594, timestamp=1668491132.7990813) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
-No: 9 GFLOPS: 2.11/14.74 result: MeasureResult(costs=(0.12725059519999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1597647666931152, timestamp=1668491135.0713344) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
-No: 10 GFLOPS: 1.81/14.74 result: MeasureResult(costs=(0.1483948042,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4889540672302246, timestamp=1668491137.6169114) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 1 GFLOPS: 12.79/12.79 result: MeasureResult(costs=(0.020986933,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.49678730964660645, timestamp=1668511322.0002625) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
+No: 2 GFLOPS: 10.73/12.79 result: MeasureResult(costs=(0.0250120642,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5861332416534424, timestamp=1668511322.608602) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+No: 3 GFLOPS: 0.51/12.79 result: MeasureResult(costs=(0.527322839,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.61455512046814, timestamp=1668511331.9650085) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+No: 4 GFLOPS: 9.10/12.79 result: MeasureResult(costs=(0.029512603000000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8305795192718506, timestamp=1668511333.3291118) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+No: 5 GFLOPS: 9.58/12.79 result: MeasureResult(costs=(0.0280191888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5838408470153809, timestamp=1668511334.0774398) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+No: 6 GFLOPS: 11.67/12.79 result: MeasureResult(costs=(0.0230074138,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5560197830200195, timestamp=1668511334.6127582) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+No: 7 GFLOPS: 8.25/12.79 result: MeasureResult(costs=(0.0325430638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6715357303619385, timestamp=1668511336.0187078) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+No: 8 GFLOPS: 3.07/12.79 result: MeasureResult(costs=(0.08744604240000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5885965824127197, timestamp=1668511337.6198728) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+No: 9 GFLOPS: 8.36/12.79 result: MeasureResult(costs=(0.0321037958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6911242008209229, timestamp=1668511338.4238167) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
+No: 10 GFLOPS: 11.13/12.79 result: MeasureResult(costs=(0.0241191274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5254871845245361, timestamp=1668511338.9775114) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
</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 a4b5388ad8..07000aadd3 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': 509.33978959999877, 'median': 509.0096936000009, 'std': 2.4713246779646143}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 512.5842140299937, 'median': 513.2335168000054, 'std': 2.1297284277345603}
</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: 6.99/ 14.73 GFLOPS | Progress: (4/20) | 10.87 s
-[Task 1/25] Current/Best: 5.78/ 23.03 GFLOPS | Progress: (8/20) | 14.80 s
-[Task 1/25] Current/Best: 12.06/ 23.03 GFLOPS | Progress: (12/20) | 16.92 s
-[Task 1/25] Current/Best: 12.88/ 23.03 GFLOPS | Progress: (16/20) | 18.66 s
-[Task 1/25] Current/Best: 13.77/ 23.03 GFLOPS | Progress: (20/20) | 21.83 s Done.
+[Task 1/25] Current/Best: 14.81/ 17.70 GFLOPS | Progress: (4/20) | 7.00 s
+[Task 1/25] Current/Best: 7.47/ 17.70 GFLOPS | Progress: (8/20) | 10.80 s
+[Task 1/25] Current/Best: 14.30/ 17.70 GFLOPS | Progress: (12/20) | 13.02 s
+[Task 1/25] Current/Best: 23.01/ 23.01 GFLOPS | Progress: (16/20) | 14.88 s
+[Task 1/25] Current/Best: 13.25/ 23.01 GFLOPS | Progress: (20/20) | 17.83 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 19.10/ 19.10 GFLOPS | Progress: (4/20) | 3.06 s
-[Task 2/25] Current/Best: 15.95/ 19.30 GFLOPS | Progress: (8/20) | 4.32 s
-[Task 2/25] Current/Best: 12.19/ 19.30 GFLOPS | Progress: (12/20) | 5.74 s
-[Task 2/25] Current/Best: 10.64/ 19.30 GFLOPS | Progress: (16/20) | 7.06 s
-[Task 2/25] Current/Best: 10.14/ 19.30 GFLOPS | Progress: (20/20) | 10.06 s Done.
+[Task 2/25] Current/Best: 19.64/ 19.91 GFLOPS | Progress: (4/20) | 3.15 s
+[Task 2/25] Current/Best: 8.62/ 19.91 GFLOPS | Progress: (8/20) | 4.25 s
+[Task 2/25] Current/Best: 20.72/ 20.72 GFLOPS | Progress: (12/20) | 5.39 s
+[Task 2/25] Current/Best: 11.20/ 20.72 GFLOPS | Progress: (16/20) | 6.96 s
+[Task 2/25] Current/Best: 15.03/ 20.72 GFLOPS | Progress: (20/20) | 7.96 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 3.15/ 16.33 GFLOPS | Progress: (4/20) | 4.15 s
-[Task 3/25] Current/Best: 13.89/ 21.09 GFLOPS | Progress: (8/20) | 6.11 s
-[Task 3/25] Current/Best: 14.02/ 21.09 GFLOPS | Progress: (12/20) | 8.18 s
-[Task 3/25] Current/Best: 17.47/ 21.09 GFLOPS | Progress: (16/20) | 12.70 s
-[Task 3/25] Current/Best: 11.51/ 21.09 GFLOPS | Progress: (20/20) | 14.50 s Done.
+[Task 3/25] Current/Best: 3.11/ 23.65 GFLOPS | Progress: (4/20) | 3.86 s
+[Task 3/25] Current/Best: 6.94/ 23.65 GFLOPS | Progress: (8/20) | 6.09 s
+[Task 3/25] Current/Best: 14.07/ 23.65 GFLOPS | Progress: (12/20) | 8.88 s
+[Task 3/25] Current/Best: 14.52/ 23.65 GFLOPS | Progress: (16/20) | 10.86 s
+[Task 3/25] Current/Best: 12.76/ 23.65 GFLOPS | Progress: (20/20) | 12.91 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.85/ 21.31 GFLOPS | Progress: (4/20) | 7.17 s
-[Task 4/25] Current/Best: 14.23/ 21.31 GFLOPS | Progress: (8/20) | 9.16 s
-[Task 4/25] Current/Best: 14.84/ 21.31 GFLOPS | Progress: (12/20) | 13.77 s
-[Task 4/25] Current/Best: 20.72/ 21.31 GFLOPS | Progress: (16/20) | 15.49 s
-[Task 4/25] Current/Best: 9.74/ 21.31 GFLOPS | Progress: (20/20) | 20.67 s Done.
+[Task 4/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (4/20) | 5.15 s
+[Task 4/25] Current/Best: 20.99/ 20.99 GFLOPS | Progress: (8/20) | 10.03 s
+[Task 4/25] Current/Best: 12.16/ 20.99 GFLOPS | Progress: (12/20) | 14.53 s
+[Task 4/25] Current/Best: 14.19/ 20.99 GFLOPS | Progress: (16/20) | 16.22 s
+[Task 4/25] Current/Best: 14.31/ 20.99 GFLOPS | Progress: (20/20) | 18.77 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 10.71/ 15.71 GFLOPS | Progress: (4/20) | 3.28 s
-[Task 5/25] Current/Best: 15.83/ 18.23 GFLOPS | Progress: (8/20) | 5.08 s
-[Task 5/25] Current/Best: 5.48/ 19.27 GFLOPS | Progress: (12/20) | 8.02 s
-[Task 5/25] Current/Best: 14.15/ 19.27 GFLOPS | Progress: (16/20) | 9.61 s
-[Task 5/25] Current/Best: 4.47/ 19.27 GFLOPS | Progress: (20/20) | 11.73 s Done.
+[Task 5/25] Current/Best: 6.69/ 13.60 GFLOPS | Progress: (4/20) | 3.46 s
+[Task 5/25] Current/Best: 5.54/ 14.82 GFLOPS | Progress: (8/20) | 5.66 s
+[Task 5/25] Current/Best: 4.08/ 14.82 GFLOPS | Progress: (12/20) | 7.69 s
+[Task 5/25] Current/Best: 14.20/ 14.82 GFLOPS | Progress: (16/20) | 11.14 s
+[Task 5/25] Current/Best: 6.43/ 20.28 GFLOPS | Progress: (20/20) | 13.06 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 15.27/ 15.30 GFLOPS | Progress: (4/20) | 4.23 s
-[Task 6/25] Current/Best: 11.93/ 19.05 GFLOPS | Progress: (8/20) | 7.81 s
-[Task 6/25] Current/Best: 5.78/ 19.05 GFLOPS | Progress: (12/20) | 10.94 s
-[Task 6/25] Current/Best: 12.94/ 20.87 GFLOPS | Progress: (16/20) | 12.84 s
-[Task 6/25] Current/Best: 16.19/ 20.87 GFLOPS | Progress: (20/20) | 15.69 s Done.
+[Task 6/25] Current/Best: 8.71/ 22.72 GFLOPS | Progress: (4/20) | 3.52 s
+[Task 6/25] Current/Best: 5.29/ 22.72 GFLOPS | Progress: (8/20) | 7.00 s
+[Task 6/25] Current/Best: 18.13/ 22.72 GFLOPS | Progress: (12/20) | 9.37 s
+[Task 6/25] Current/Best: 12.77/ 22.72 GFLOPS | Progress: (16/20) | 12.12 s
+[Task 6/25] Current/Best: 2.88/ 22.72 GFLOPS | Progress: (20/20) | 15.35 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 17.53/ 17.53 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 7/25] Current/Best: 15.67/ 17.53 GFLOPS | Progress: (8/20) | 5.63 s
-[Task 7/25] Current/Best: 15.58/ 19.15 GFLOPS | Progress: (12/20) | 7.26 s
-[Task 7/25] Current/Best: 21.89/ 22.43 GFLOPS | Progress: (16/20) | 8.95 s
-[Task 7/25] Current/Best: 14.61/ 22.43 GFLOPS | Progress: (20/20) | 11.71 s Done.
+[Task 7/25] Current/Best: 13.38/ 17.92 GFLOPS | Progress: (4/20) | 3.56 s
+[Task 7/25] Current/Best: 18.67/ 18.67 GFLOPS | Progress: (8/20) | 5.49 s
+[Task 7/25] Current/Best: 12.21/ 18.67 GFLOPS | Progress: (12/20) | 7.81 s
+[Task 7/25] Current/Best: 11.90/ 18.67 GFLOPS | Progress: (16/20) | 10.37 s
+[Task 7/25] Current/Best: 9.62/ 18.67 GFLOPS | Progress: (20/20) | 12.60 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 12.55/ 15.42 GFLOPS | Progress: (4/20) | 4.68 s
-[Task 8/25] Current/Best: 11.49/ 15.42 GFLOPS | Progress: (8/20) | 7.02 s
-[Task 8/25] Current/Best: 10.78/ 15.42 GFLOPS | Progress: (12/20) | 14.16 s
-[Task 8/25] Current/Best: 17.80/ 17.80 GFLOPS | Progress: (16/20) | 16.58 s
-[Task 8/25] Current/Best: 12.25/ 17.80 GFLOPS | Progress: (20/20) | 27.45 s
+[Task 8/25] Current/Best: 14.79/ 20.43 GFLOPS | Progress: (4/20) | 3.25 s
+[Task 8/25] Current/Best: 10.53/ 20.43 GFLOPS | Progress: (8/20) | 14.08 s
+[Task 8/25] Current/Best: 11.48/ 20.43 GFLOPS | Progress: (12/20) | 16.60 s
+[Task 8/25] Current/Best: 5.44/ 20.43 GFLOPS | Progress: (16/20) | 20.25 s
+[Task 8/25] Current/Best: 7.29/ 20.43 GFLOPS | Progress: (20/20) | 22.36 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 11.76/ 14.46 GFLOPS | Progress: (4/20) | 7.32 s
-[Task 9/25] Current/Best: 22.24/ 22.24 GFLOPS | Progress: (8/20) | 8.60 s
-[Task 9/25] Current/Best: 6.48/ 22.24 GFLOPS | Progress: (12/20) | 12.37 s
-[Task 9/25] Current/Best: 17.58/ 22.24 GFLOPS | Progress: (16/20) | 18.48 s
-[Task 9/25] Current/Best: 11.61/ 22.24 GFLOPS | Progress: (20/20) | 22.80 s Done.
-
+[Task 9/25] Current/Best: 11.33/ 13.25 GFLOPS | Progress: (4/20) | 4.58 s
+[Task 9/25] Current/Best: 20.35/ 20.39 GFLOPS | Progress: (8/20) | 14.90 s
+[Task 9/25] Current/Best: 11.48/ 20.39 GFLOPS | Progress: (12/20) | 17.68 s
+[Task 9/25] Current/Best: 13.91/ 20.39 GFLOPS | Progress: (16/20) | 28.42 s
+[Task 9/25] Current/Best: 18.70/ 20.39 GFLOPS | Progress: (20/20) | 39.31 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 14.13/ 19.07 GFLOPS | Progress: (4/20) | 2.96 s
-[Task 10/25] Current/Best: 12.45/ 19.07 GFLOPS | Progress: (8/20) | 5.27 s
-[Task 10/25] Current/Best: 10.37/ 19.07 GFLOPS | Progress: (12/20) | 7.06 s
-[Task 10/25] Current/Best: 10.99/ 19.07 GFLOPS | Progress: (16/20) | 9.66 s
-[Task 10/25] Current/Best: 4.35/ 19.07 GFLOPS | Progress: (20/20) | 11.23 s Done.
+[Task 10/25] Current/Best: 9.56/ 20.48 GFLOPS | Progress: (4/20) | 2.79 s
+[Task 10/25] Current/Best: 20.27/ 20.83 GFLOPS | Progress: (8/20) | 4.37 s
+[Task 10/25] Current/Best: 13.13/ 20.83 GFLOPS | Progress: (12/20) | 6.77 s
+[Task 10/25] Current/Best: 5.30/ 20.83 GFLOPS | Progress: (16/20) | 10.62 s
+[Task 10/25] Current/Best: 11.38/ 20.83 GFLOPS | Progress: (20/20) | 12.36 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 10.54/ 12.42 GFLOPS | Progress: (4/20) | 4.17 s
-[Task 11/25] Current/Best: 3.17/ 18.81 GFLOPS | Progress: (8/20) | 6.65 s
-[Task 11/25] Current/Best: 13.89/ 18.81 GFLOPS | Progress: (12/20) | 9.01 s
-[Task 11/25] Current/Best: 9.88/ 18.81 GFLOPS | Progress: (16/20) | 10.86 s
-[Task 11/25] Current/Best: 8.40/ 18.89 GFLOPS | Progress: (20/20) | 13.13 s Done.
+[Task 11/25] Current/Best: 13.20/ 13.20 GFLOPS | Progress: (4/20) | 4.66 s
+[Task 11/25] Current/Best: 11.48/ 18.62 GFLOPS | Progress: (8/20) | 6.61 s Done.
+ Done.
+
+[Task 11/25] Current/Best: 22.87/ 22.87 GFLOPS | Progress: (12/20) | 9.40 s
+[Task 11/25] Current/Best: 8.78/ 22.87 GFLOPS | Progress: (16/20) | 11.75 s
+[Task 11/25] Current/Best: 6.25/ 22.87 GFLOPS | Progress: (20/20) | 14.10 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.86/ 14.35 GFLOPS | Progress: (4/20) | 3.91 s
-[Task 12/25] Current/Best: 12.58/ 14.35 GFLOPS | Progress: (8/20) | 9.68 s
-[Task 12/25] Current/Best: 12.28/ 16.66 GFLOPS | Progress: (12/20) | 18.57 s
-[Task 12/25] Current/Best: 11.15/ 16.66 GFLOPS | Progress: (16/20) | 20.67 s
-[Task 12/25] Current/Best: 6.02/ 21.36 GFLOPS | Progress: (20/20) | 22.84 s Done.
+[Task 12/25] Current/Best: 15.60/ 18.68 GFLOPS | Progress: (4/20) | 3.91 s
+[Task 12/25] Current/Best: 12.62/ 18.68 GFLOPS | Progress: (8/20) | 5.88 s
+[Task 12/25] Current/Best: 12.96/ 18.68 GFLOPS | Progress: (12/20) | 9.91 s
+[Task 12/25] Current/Best: 11.59/ 18.68 GFLOPS | Progress: (16/20) | 11.64 s
+[Task 12/25] Current/Best: 15.08/ 18.68 GFLOPS | Progress: (20/20) | 13.52 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 6.26/ 14.04 GFLOPS | Progress: (4/20) | 4.82 s
-[Task 13/25] Current/Best: 11.21/ 14.04 GFLOPS | Progress: (8/20) | 8.28 s
-[Task 13/25] Current/Best: 8.71/ 21.17 GFLOPS | Progress: (12/20) | 10.22 s
-[Task 13/25] Current/Best: 16.94/ 21.17 GFLOPS | Progress: (16/20) | 12.34 s
-[Task 13/25] Current/Best: 5.93/ 21.17 GFLOPS | Progress: (20/20) | 14.77 s Done.
+[Task 13/25] Current/Best: 6.17/ 20.50 GFLOPS | Progress: (4/20) | 5.29 s
+[Task 13/25] Current/Best: 17.83/ 20.50 GFLOPS | Progress: (8/20) | 8.53 s
+[Task 13/25] Current/Best: 19.44/ 20.50 GFLOPS | Progress: (12/20) | 11.79 s
+[Task 13/25] Current/Best: 15.53/ 20.50 GFLOPS | Progress: (16/20) | 14.15 s
+[Task 13/25] Current/Best: 13.39/ 20.50 GFLOPS | Progress: (20/20) | 16.10 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 1.53/ 14.75 GFLOPS | Progress: (4/20) | 5.77 s
-[Task 14/25] Current/Best: 9.68/ 14.75 GFLOPS | Progress: (8/20) | 10.23 s
-[Task 14/25] Current/Best: 13.13/ 14.75 GFLOPS | Progress: (12/20) | 12.14 s
-[Task 14/25] Current/Best: 2.78/ 14.75 GFLOPS | Progress: (16/20) | 17.80 s Done.
-
-[Task 14/25] Current/Best: 14.76/ 14.76 GFLOPS | Progress: (20/20) | 20.31 s Done.
-
+[Task 14/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (4/20) | 3.61 s
+[Task 14/25] Current/Best: 18.80/ 20.61 GFLOPS | Progress: (8/20) | 4.98 s
+[Task 14/25] Current/Best: 15.17/ 20.61 GFLOPS | Progress: (12/20) | 8.18 s
+[Task 14/25] Current/Best: 15.24/ 20.61 GFLOPS | Progress: (16/20) | 10.59 s
+[Task 14/25] Current/Best: 8.42/ 20.61 GFLOPS | Progress: (20/20) | 14.64 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 17.45/ 20.78 GFLOPS | Progress: (4/20) | 2.85 s
-[Task 15/25] Current/Best: 21.02/ 21.02 GFLOPS | Progress: (8/20) | 6.69 s
-[Task 15/25] Current/Best: 22.63/ 22.63 GFLOPS | Progress: (12/20) | 8.91 s
-[Task 15/25] Current/Best: 16.76/ 22.63 GFLOPS | Progress: (16/20) | 10.75 s
-[Task 15/25] Current/Best: 12.12/ 22.63 GFLOPS | Progress: (20/20) | 12.11 s
+[Task 15/25] Current/Best: 4.85/ 17.95 GFLOPS | Progress: (4/20) | 4.34 s
+[Task 15/25] Current/Best: 6.15/ 19.44 GFLOPS | Progress: (8/20) | 6.31 s
+[Task 15/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (12/20) | 11.78 s
+[Task 15/25] Current/Best: 4.14/ 19.51 GFLOPS | Progress: (16/20) | 13.40 s
+[Task 15/25] Current/Best: 6.49/ 19.51 GFLOPS | Progress: (20/20) | 16.06 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 4.33/ 14.13 GFLOPS | Progress: (4/20) | 4.02 s
-[Task 16/25] Current/Best: 10.56/ 14.32 GFLOPS | Progress: (8/20) | 7.50 s
-[Task 16/25] Current/Best: 4.66/ 16.14 GFLOPS | Progress: (12/20) | 9.38 s
-[Task 16/25] Current/Best: 10.03/ 16.14 GFLOPS | Progress: (16/20) | 10.73 s
-[Task 16/25] Current/Best: 6.17/ 16.17 GFLOPS | Progress: (20/20) | 12.35 s Done.
+[Task 16/25] Current/Best: 9.24/ 12.69 GFLOPS | Progress: (4/20) | 4.61 s
+[Task 16/25] Current/Best: 3.62/ 20.06 GFLOPS | Progress: (8/20) | 6.67 s
+[Task 16/25] Current/Best: 14.45/ 20.06 GFLOPS | Progress: (12/20) | 8.27 s
+[Task 16/25] Current/Best: 16.91/ 20.06 GFLOPS | Progress: (16/20) | 9.54 s
+[Task 16/25] Current/Best: 18.25/ 20.06 GFLOPS | Progress: (20/20) | 11.08 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 15.70/ 19.12 GFLOPS | Progress: (4/20) | 4.66 s
-[Task 17/25] Current/Best: 19.05/ 20.36 GFLOPS | Progress: (8/20) | 6.68 s
-[Task 17/25] Current/Best: 10.14/ 20.36 GFLOPS | Progress: (12/20) | 8.94 s
-[Task 17/25] Current/Best: 10.20/ 20.36 GFLOPS | Progress: (16/20) | 11.42 s
-[Task 17/25] Current/Best: 22.83/ 22.83 GFLOPS | Progress: (20/20) | 13.68 s Done.
+[Task 17/25] Current/Best: 1.56/ 18.45 GFLOPS | Progress: (4/20) | 5.20 s
+[Task 17/25] Current/Best: 9.99/ 21.77 GFLOPS | Progress: (8/20) | 7.93 s Done.
+ Done.
+
+[Task 17/25] Current/Best: 10.12/ 21.77 GFLOPS | Progress: (12/20) | 10.12 s
+[Task 17/25] Current/Best: 12.25/ 21.77 GFLOPS | Progress: (16/20) | 12.71 s
+[Task 17/25] Current/Best: 16.28/ 21.77 GFLOPS | Progress: (20/20) | 15.41 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 10.80/ 14.08 GFLOPS | Progress: (4/20) | 7.52 s
-[Task 18/25] Current/Best: 10.34/ 18.02 GFLOPS | Progress: (8/20) | 11.91 s
-[Task 18/25] Current/Best: 3.11/ 19.97 GFLOPS | Progress: (12/20) | 14.10 s
-[Task 18/25] Current/Best: 9.55/ 19.97 GFLOPS | Progress: (16/20) | 18.24 s
-[Task 18/25] Current/Best: 9.14/ 20.39 GFLOPS | Progress: (20/20) | 20.03 s Done.
+[Task 18/25] Current/Best: 11.68/ 18.07 GFLOPS | Progress: (4/20) | 4.58 s
+[Task 18/25] Current/Best: 16.03/ 18.07 GFLOPS | Progress: (8/20) | 6.36 s
+[Task 18/25] Current/Best: 3.07/ 18.07 GFLOPS | Progress: (12/20) | 8.83 s
+[Task 18/25] Current/Best: 14.93/ 18.07 GFLOPS | Progress: (16/20) | 12.14 s
+[Task 18/25] Current/Best: 3.01/ 18.07 GFLOPS | Progress: (20/20) | 17.97 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 6.67/ 21.08 GFLOPS | Progress: (4/20) | 4.78 s
-[Task 19/25] Current/Best: 11.20/ 21.08 GFLOPS | Progress: (8/20) | 8.18 s
-[Task 19/25] Current/Best: 11.11/ 21.08 GFLOPS | Progress: (12/20) | 10.79 s
-[Task 19/25] Current/Best: 12.76/ 21.08 GFLOPS | Progress: (16/20) | 13.56 s
-[Task 19/25] Current/Best: 11.10/ 21.08 GFLOPS | Progress: (20/20) | 16.20 s Done.
+[Task 19/25] Current/Best: 11.71/ 21.70 GFLOPS | Progress: (4/20) | 3.51 s
+[Task 19/25] Current/Best: 6.19/ 21.70 GFLOPS | Progress: (8/20) | 6.55 s
+[Task 19/25] Current/Best: 7.65/ 21.70 GFLOPS | Progress: (12/20) | 9.64 s
+[Task 19/25] Current/Best: 7.44/ 21.70 GFLOPS | Progress: (16/20) | 12.33 s
+[Task 19/25] Current/Best: 12.23/ 21.70 GFLOPS | Progress: (20/20) | 17.81 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 4.73/ 15.87 GFLOPS | Progress: (4/20) | 3.46 s
-[Task 20/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (8/20) | 5.58 s
-[Task 20/25] Current/Best: 7.80/ 20.63 GFLOPS | Progress: (12/20) | 9.86 s Done.
+[Task 20/25] Current/Best: 9.44/ 13.96 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 20/25] Current/Best: 13.91/ 13.96 GFLOPS | Progress: (8/20) | 5.66 s
+[Task 20/25] Current/Best: 10.26/ 13.96 GFLOPS | Progress: (12/20) | 7.82 s
+[Task 20/25] Current/Best: 13.55/ 16.62 GFLOPS | Progress: (16/20) | 10.49 s
+[Task 20/25] Current/Best: 16.78/ 18.38 GFLOPS | Progress: (20/20) | 12.57 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 21/25] Current/Best: 5.37/ 19.38 GFLOPS | Progress: (4/20) | 6.58 s
+[Task 21/25] Current/Best: 16.22/ 19.38 GFLOPS | Progress: (8/20) | 7.81 s
+[Task 21/25] Current/Best: 13.24/ 19.38 GFLOPS | Progress: (12/20) | 9.39 s
+[Task 21/25] Current/Best: 18.86/ 19.38 GFLOPS | Progress: (16/20) | 11.81 s Done.
-[Task 20/25] Current/Best: 14.72/ 20.63 GFLOPS | Progress: (16/20) | 13.09 s
-[Task 20/25] Current/Best: 7.84/ 20.63 GFLOPS | Progress: (20/20) | 15.49 s Done.
+[Task 21/25] Current/Best: 19.10/ 19.38 GFLOPS | Progress: (20/20) | 13.21 s Done.
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 15.77/ 15.77 GFLOPS | Progress: (4/20) | 2.83 s
-[Task 21/25] Current/Best: 18.00/ 18.00 GFLOPS | Progress: (8/20) | 5.15 s
-[Task 21/25] Current/Best: 5.41/ 19.10 GFLOPS | Progress: (12/20) | 8.04 s
-[Task 21/25] Current/Best: 7.75/ 19.10 GFLOPS | Progress: (16/20) | 10.07 s
-[Task 21/25] Current/Best: 18.37/ 19.10 GFLOPS | Progress: (20/20) | 11.36 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 16.82/ 22.23 GFLOPS | Progress: (4/20) | 3.98 s
-[Task 22/25] Current/Best: 11.42/ 22.23 GFLOPS | Progress: (8/20) | 5.91 s
-[Task 22/25] Current/Best: 9.54/ 22.23 GFLOPS | Progress: (12/20) | 7.45 s
-[Task 22/25] Current/Best: 16.32/ 22.23 GFLOPS | Progress: (16/20) | 8.71 s
-[Task 22/25] Current/Best: 6.02/ 22.23 GFLOPS | Progress: (20/20) | 11.70 s Done.
+[Task 22/25] Current/Best: 10.61/ 12.75 GFLOPS | Progress: (4/20) | 3.12 s
+[Task 22/25] Current/Best: 10.19/ 15.48 GFLOPS | Progress: (8/20) | 5.20 s
+[Task 22/25] Current/Best: 7.30/ 21.20 GFLOPS | Progress: (12/20) | 7.60 s
+[Task 22/25] Current/Best: 10.70/ 21.20 GFLOPS | Progress: (16/20) | 9.34 s
+[Task 22/25] Current/Best: 5.11/ 21.20 GFLOPS | Progress: (20/20) | 10.72 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 11.26/ 17.23 GFLOPS | Progress: (4/20) | 4.29 s
-[Task 23/25] Current/Best: 12.17/ 19.54 GFLOPS | Progress: (8/20) | 7.04 s
-[Task 23/25] Current/Best: 13.59/ 19.54 GFLOPS | Progress: (12/20) | 11.61 s
-[Task 23/25] Current/Best: 18.74/ 19.54 GFLOPS | Progress: (16/20) | 14.02 s
-[Task 23/25] Current/Best: 10.23/ 19.54 GFLOPS | Progress: (20/20) | 15.96 s Done.
+[Task 23/25] Current/Best: 23.37/ 23.37 GFLOPS | Progress: (4/20) | 3.99 s
+[Task 23/25] Current/Best: 7.94/ 23.37 GFLOPS | Progress: (8/20) | 6.68 s
+[Task 23/25] Current/Best: 12.03/ 23.37 GFLOPS | Progress: (12/20) | 8.73 s
+[Task 23/25] Current/Best: 17.25/ 23.37 GFLOPS | Progress: (16/20) | 12.99 s
+[Task 23/25] Current/Best: 10.75/ 23.37 GFLOPS | Progress: (20/20) | 16.68 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 3.32/ 5.25 GFLOPS | Progress: (4/20) | 12.23 s
-[Task 24/25] Current/Best: 1.72/ 7.94 GFLOPS | Progress: (8/20) | 18.15 s
-[Task 24/25] Current/Best: 7.83/ 7.94 GFLOPS | Progress: (12/20) | 28.84 s
-[Task 24/25] Current/Best: 7.93/ 7.94 GFLOPS | Progress: (16/20) | 39.57 s
-[Task 24/25] Current/Best: 7.82/ 9.95 GFLOPS | Progress: (20/20) | 41.36 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 25/25] Current/Best: 5.89/ 7.32 GFLOPS | Progress: (4/20) | 12.29 s
-[Task 25/25] Current/Best: 9.38/ 9.38 GFLOPS | Progress: (8/20) | 20.57 s
-[Task 25/25] Current/Best: 8.38/ 9.38 GFLOPS | Progress: (12/20) | 21.63 s
-[Task 25/25] Current/Best: 6.09/ 9.38 GFLOPS | Progress: (16/20) | 22.74 s
-[Task 25/25] Current/Best: 5.61/ 9.38 GFLOPS | Progress: (20/20) | 27.80 s
+[Task 24/25] Current/Best: 8.19/ 8.19 GFLOPS | Progress: (4/20) | 12.18 s
+[Task 24/25] Current/Best: 3.57/ 10.91 GFLOPS | Progress: (8/20) | 18.26 s
+[Task 24/25] Current/Best: 6.16/ 10.91 GFLOPS | Progress: (12/20) | 28.90 s
+[Task 24/25] Current/Best: 2.30/ 10.91 GFLOPS | Progress: (16/20) | 32.92 s
+[Task 24/25] Current/Best: 9.91/ 10.91 GFLOPS | Progress: (20/20) | 43.37 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 1.54/ 8.03 GFLOPS | Progress: (4/20) | 4.42 s Done.
+
+[Task 25/25] Current/Best: 4.24/ 8.03 GFLOPS | Progress: (8/20) | 15.13 s
+[Task 25/25] Current/Best: 3.52/ 8.03 GFLOPS | Progress: (12/20) | 16.84 s
+[Task 25/25] Current/Best: 9.48/ 9.48 GFLOPS | Progress: (16/20) | 27.12 s
+[Task 25/25] Current/Best: 3.45/ 9.48 GFLOPS | Progress: (20/20) | 37.61 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -945,8 +945,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
... 260 lines suppressed ...