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 2022/07/26 03:48:47 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@9963b59ffa489db61358dedd35a2453a5ca666b9)
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 53779f48e deploying docs (apache/tvm@9963b59ffa489db61358dedd35a2453a5ca666b9)
53779f48e is described below
commit 53779f48efeb632bdbc82cac0aceb7cd05683cd7
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Jul 26 03:48:42 2022 +0000
deploying docs (apache/tvm@9963b59ffa489db61358dedd35a2453a5ca666b9)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 16 +-
.../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 | 1898 ++++++--------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 135 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 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 | 2 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 51 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 50 +-
docs/how_to/deploy_models/deploy_prequantized.html | 13 +-
.../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 | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../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 | 1898 ++++++--------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 135 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/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 | 2 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 47 +-
121 files changed, 1943 insertions(+), 3743 deletions(-)
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 730624a54..366532a85 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.804 seconds)
+ **Total running time of the script:** ( 1 minutes 2.256 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 1b6073f83..1deea06c7 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.zipe79293e5-13ee-446d-b6dc-eb566eab2105 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip241cd94a-0a75-467f-90bb-913710ef9eef 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 7f6094bb9..80b539df1 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 58.6MB/s]
29%|##8 | 11.9M/41.5M [00:00<00:00, 44.7MB/s]
39%|###9 | 16.3M/41.5M [00:00<00:01, 24.4MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 32.8MB/s]
64%|######3 | 26.4M/41.5M [00:00<00:00, 27.8MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 33.6MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 37.8MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 34.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 64.9MB/s]
30%|### | 12.5M/41.5M [00:00<00:00, 62.6MB/s]
45%|####4 | 18.5M/41.5M [00:00<00:00, 32.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.7MB/s]
80%|######## | 33.4M/41.5M [00:00<00:00, 48.9MB/s]
95%|#########4| 39.2M/41.5M [00:00<00:00, 51.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 43.8MB/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 c30930003..685330d18 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
8%|7 | 3.45M/44.7M [00:00<00:01, 36.1MB/s]
17%|#6 | 7.40M/44.7M [00:00<00:00, 39.2MB/s]
73%|#######2 | 32.4M/44.7M [00:00<00:00, 141MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 134MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
43%|####2 | 19.1M/44.7M [00:00<00:00, 199MB/s]
98%|#########8| 43.8M/44.7M [00:00<00:00, 235MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 231MB/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 8d2bf720e..c6c5451f4 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.897 seconds)
+ **Total running time of the script:** ( 1 minutes 2.235 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 7224bb1ae..990777aa5 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:07.112** total execution time for **how_to_compile_models** files:
+**04:59.514** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.804 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:02.256 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.897 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.235 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.109 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.737 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.942 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.344 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.609 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.382 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.537 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.472 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.512 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.892 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.197 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.800 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.109 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.626 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.397 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.769 | 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 9cc2aecd8..3d08ea0f7 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0137 16.0081 16.1106 15.9247 0.0619
+ 15.8462 15.8432 16.0139 15.6569 0.0882
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 28e4a5b98..b996d5b84 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.56M/170M [00:00<00:03, 46.5MB/s]
5%|5 | 9.00M/170M [00:00<00:03, 42.5MB/s]
8%|7 | 13.1M/170M [00:00<00:04, 38.4MB/s]
10%|9 | 16.8M/170M [00:00<00:04, 33.3MB/s]
12%|#1 | 20.0M/170M [00:00<00:05, 31.2MB/s]
15%|#4 | 25.1M/170M [00:00<00:04, 37.4MB/s]
18%|#7 | 30.1M/170M [00:00<00:03, 41.6MB/s]
20%|## | 34.2M/170M [00:01<00:04, 31.7MB/s]
23%|##2 | 38.4M/170M [00:01<00:03, 34.6MB/s]
26%|##5 | 43.7M/170M [00:01<00:03, 39.9MB/s]
29%|##8 | 48.5M/170M [00:01<00:03, 41.5MB/s]
31%|###1 | 52.8M/170M [00:01<00:03, 38.7MB/s]
33%|###3 | 56.7M/170M [00:01<00:03, 39.2MB/s]
36%|###6 | 61.2M/170M [00:01<00:02, 41.4MB/s]
39%|###8 | 65.9M/170M [00:01<00:02, 43.3MB/s]
41%|####1 | 70.1M/170M [00:01<00:02, 40.2MB/s]
44%|####3 | 74.4M/170M [00:02<00:02, 41.4MB/
s]
46%|####6 | 78.6M/170M [00:02<00:02, 42.0MB/s]
49%|####8 | 82.6M/170M [00:02<00:02, 39.7MB/s]
51%|#####1 | 86.6M/170M [00:02<00:02, 40.2MB/s]
53%|#####3 | 90.5M/170M [00:02<00:02, 37.8MB/s]
57%|#####6 | 96.3M/170M [00:02<00:01, 44.0MB/s]
59%|#####9 | 101M/170M [00:02<00:01, 42.3MB/s]
62%|######2 | 105M/170M [00:02<00:01, 44.4MB/s]
65%|######4 | 110M/170M [00:02<00:01, 41.4MB/s]
68%|######7 | 115M/170M [00:03<00:01, 45.3MB/s]
71%|####### | 120M/170M [00:03<00:01, 46.7MB/s]
73%|#######3 | 124M/170M [00:03<00:01, 41.6MB/s]
76%|#######5 | 129M/170M [00:03<00:00, 43.6MB/s]
79%|#######8 | 133M/170M [00:03<00:00, 41.5MB/s]
81%|########1 | 138M/170M [00:03<00:00, 42.4MB/s]
84%|########4 | 143M/170M [00:03<00:00, 45.5MB/s]
87%|########6 | 147M/170M [00:03<00:00, 45.2MB/s]
89%|########9 | 152M/170M [00:03<00:00, 42.4MB/s]
92%|#########1| 156M/170M [00:04<00:00, 41.8MB/s
]
94%|#########4| 160M/170M [00:04<00:00, 38.0MB/s]
96%|#########6| 163M/170M [00:04<00:00, 37.0MB/s]
98%|#########8| 167M/170M [00:04<00:00, 35.2MB/s]
100%|##########| 170M/170M [00:04<00:00, 39.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
10%|9 | 16.8M/170M [00:00<00:00, 176MB/s]
21%|##1 | 36.1M/170M [00:00<00:00, 192MB/s]
32%|###2 | 54.6M/170M [00:00<00:00, 192MB/s]
43%|####2 | 72.9M/170M [00:00<00:00, 185MB/s]
57%|#####6 | 96.5M/170M [00:00<00:00, 207MB/s]
70%|####### | 119M/170M [00:00<00:00, 218MB/s]
83%|########2 | 140M/170M [00:00<00:00, 189MB/s]
94%|#########3| 159M/170M [00:00<00:00, 192MB/s]
100%|##########| 170M/170M [00:00<00:00, 196MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 5.150 seconds)
+ **Total running time of the script:** ( 2 minutes 58.525 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 c587fc7a3..11dabed32 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
4%|3 | 528k/13.6M [00:00<00:02, 5.38MB/s]
12%|#1 | 1.59M/13.6M [00:00<00:01, 8.85MB/s]
21%|##1 | 2.86M/13.6M [00:00<00:01, 10.9MB/s]
33%|###2 | 4.46M/13.6M [00:00<00:00, 13.2MB/s]
47%|####7 | 6.41M/13.6M [00:00<00:00, 15.8MB/s]
65%|######5 | 8.84M/13.6M [00:00<00:00, 19.0MB/s]
87%|########6 | 11.7M/13.6M [00:00<00:00, 22.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 18.8MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 157MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4538 90.2867 101.4936 90.1615 1.1237
+ 90.2781 90.2287 91.5704 89.9942 0.2159
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.329 seconds)
+ **Total running time of the script:** ( 1 minutes 8.453 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 8f3f0a362..f878fbb9e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.6525 119.5073 123.2438 118.9992 0.6467
+ 120.2829 120.1988 126.0842 119.5414 0.6776
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 3.537 seconds)
+ **Total running time of the script:** ( 1 minutes 57.067 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 7bc7ee11e..21455b4db 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 30.584 seconds)
+ **Total running time of the script:** ( 1 minutes 31.339 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 0624894b6..c470a83fb 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4365/132723 [00:00<00:02, 43639.95KB/s]
9%|8 | 11901/132723 [00:00<00:01, 62290.78KB/s]
14%|#3 | 18131/132723 [00:00<00:02, 50855.93KB/s]
20%|## | 26660/132723 [00:00<00:01, 62817.80KB/s]
25%|##5 | 33229/132723 [00:00<00:01, 50168.26KB/s]
31%|###1 | 41601/132723 [00:00<00:01, 59276.56KB/s]
37%|###7 | 49140/132723 [00:00<00:01, 59984.19KB/s]
43%|####3 | 57153/132723 [00:00<00:01, 65480.59KB/s]
49%|####9 | 65523/132723 [00:01<00:01, 61634.85KB/s]
55%|#####4 | 72814/132723 [00:01<00:00, 64555.58KB/s]
61%|######1 | 81357/132723 [00:01<00:00, 70194.05KB/s]
67%|######6 | 88633/132723 [00:01<00:00, 61920.36KB/s]
73%|#######3 | 97136/132723 [00:01<00:00, 67877.13KB/s]
80%|#######9 | 105644/132723 [00:01<00:00, 72507.04KB/s]
86%|########6 | 114235/132723 [00:01<00:00, 76223.83KB/s]
92%|#########
2| 122518/132723 [00:01<00:00, 78097.99KB/s]
99%|#########8| 131023/132723 [00:01<00:00, 80103.50KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67048.15KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 4856/132723 [00:00<00:02, 47656.08KB/s]
8%|8 | 10687/132723 [00:00<00:02, 53870.66KB/s]
15%|#4 | 19272/132723 [00:00<00:01, 68408.18KB/s]
21%|##1 | 27923/132723 [00:00<00:01, 75532.91KB/s]
28%|##7 | 36551/132723 [00:00<00:01, 79400.35KB/s]
34%|###4 | 45265/132723 [00:00<00:01, 82027.29KB/s]
40%|#### | 53565/132723 [00:00<00:00, 82340.52KB/s]
47%|####6 | 61969/132723 [00:00<00:00, 82878.94KB/s]
53%|#####2 | 70259/132723 [00:00<00:00, 77624.42KB/s]
60%|#####9 | 78975/132723 [00:01<00:00, 80433.90KB/s]
66%|######5 | 87077/132723 [00:01<00:00, 70062.47KB/s]
72%|#######2 | 95777/132723 [00:01<00:00, 74617.15KB/s]
78%|#######7 | 103480/132723 [00:01<00:00, 71229.01KB/s]
84%|########4 | 112086/132723 [00:01<00:00, 75273.48KB/s]
90%|######### | 119784/132723 [00:01<00:00, 42716.31KB/s]
97%|########
#6| 128470/132723 [00:01<00:00, 50850.70KB/s]
100%|##########| 132723/132723 [00:02<00:00, 65178.89KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 34.802 seconds)
+ **Total running time of the script:** ( 2 minutes 32.562 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 36a693dc2..bbc91cafa 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**11:17.478** total execution time for **how_to_deploy_models** files:
+**11:00.195** 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``) | 03:05.150 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:58.525 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:34.802 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:32.562 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:03.537 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:57.067 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:30.584 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:31.339 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.329 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.453 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.945 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.483 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.125 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.760 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index f2d55b50c..15334da41 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa09fc72a-76bb-4028-ba1b-cfa89ad94b70 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip1b5687ac-8be1-4d2a-8e84-6db2dd5730f0 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 285a06901..8ce9b074f 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:41.145** total execution time for **how_to_extend_tvm** files:
+**00:40.169** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.878 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.310 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.226 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.949 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.928 | 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 014540591..8c5133de7 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: 6775us [6775us] (46.02%; 46.02%)
- FoldScaleAxis: 7947us [6us] (53.98%; 53.98%)
- FoldConstant: 7941us [1643us] (53.94%; 99.92%)
- InferType: 6298us [6298us] (42.78%; 79.31%)
+ InferType: 6742us [6742us] (45.85%; 45.85%)
+ FoldScaleAxis: 7963us [6us] (54.15%; 54.15%)
+ FoldConstant: 7957us [1608us] (54.11%; 99.93%)
+ InferType: 6349us [6349us] (43.18%; 79.79%)
@@ -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: 6291us [6291us] (44.54%; 44.54%)
- FoldScaleAxis: 7834us [5us] (55.46%; 55.46%)
- FoldConstant: 7829us [1650us] (55.43%; 99.94%)
- InferType: 6179us [6179us] (43.75%; 78.92%)
+ InferType: 6549us [6549us] (45.16%; 45.16%)
+ FoldScaleAxis: 7952us [5us] (54.84%; 54.84%)
+ FoldConstant: 7946us [1654us] (54.80%; 99.93%)
+ InferType: 6292us [6292us] (43.39%; 79.18%)
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
index d53a818a3..7f0c9e9f6 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: 37.951357 ms
+ Convolution: 33.218063 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 93d37f507..d4d2c9537 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 11.651502 ms
+ conv2d with tensor core: 8.231977 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 e61811c8e..0857f68bf 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: 0.019570
- Baseline: 3.356191
+ Numpy running time: 0.019313
+ Baseline: 3.259689
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.313325
+ Opt1: 0.298590
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.346535
+ Opt2: 0.337184
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116763
+ Opt3: 0.119793
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110824
+ Opt4: 0.111383
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111837
+ Opt5: 0.111500
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145436
+ Opt6: 0.144905
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 17ed07dfe..da6de2cfd 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.741** total execution time for **how_to_optimize_operators** files:
+**00:34.015** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.451 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.846 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.289 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.224 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.945 | 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 5238fdc51..09ccbaf9e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:03.618** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:02.992** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:16.739 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:18.616 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.138 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.693 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.342 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.736 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.025 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.920 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.785 | 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 ddc7060b8..8bdd62ea2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,12 +240,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [192]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=64)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -253,704 +253,298 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[15] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (rc.outer.outer*392)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[(threadIdx.x_1*2)] = @tir.if_then_else((((7 <= floormod((threadIdx.x_1*2), 63)) && (floormod((threadIdx.x_1*2), 63) < 56)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[(((cse_var_2 + (floordiv((threadIdx.x_1*2), 63)*49)) + floormod((threadIdx.x_1*2), 63)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else((((7 <= floormod(((threadIdx.x_1*2) + 1), 63)) && (floormod(((threadIdx.x_1*2) + 1), 63) < 56)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[(((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 63)*49)) + floormod(((threadIdx.x_1*2) + 1), 63)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 343)] = @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 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 441)] = @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 + 441), 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @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 + 490), 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 539)] = @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 + 539), 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @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 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 11), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else((((threadIdx.x_1 < 2) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + (threadIdx.x_1 + 7)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 98), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 98), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threa [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 99), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 99), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 196), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 196), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((thr [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 197), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 197), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 294), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 294), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((thr [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 295), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 295), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 392), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((thr [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 393), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv((threadIdx.x_1*2), 7) + 7)*7) + floormod((threadIdx.x_1*2), 7)) + 441)] = @tir.if_then_else((((threadIdx.x_1*2) < 7) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((cse_var_2 + (threadIdx.x_1*2)) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[(threadIdx.x_2*32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*32), 72), 3)*3)) + floormod((threadIdx.x_2*2), 3))]
}
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv(((threadIdx.x_1*2) + 1), 7) + 7)*7) + floormod(((threadIdx.x_1*2) + 1), 7)) + 441)] = @tir.if_then_else(((((threadIdx.x_1*2) + 1) < 7) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((cse_var_2 + ((threadIdx.x_1*2) + 1)) + 384)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 1), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
}
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [192], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 1), 24)*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 24)*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 45), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 24)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[0]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[48]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[72]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[1]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[49]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[73]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[2]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[50]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[74]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[51]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[75]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[4]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[52]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[76]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[5]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[53]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[77]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[54]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[78]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[7]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[55]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[79]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[8]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[56]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[80]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[57]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[81]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[10]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[58]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[82]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[11]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[59]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[83]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[96]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[120]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[144]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[168]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[97]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[121]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[145]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[169]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[98]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[122]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[146]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[170]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[123]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[147]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[171]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[100]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[124]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[148]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[172]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[101]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[125]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[149]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[173]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[126]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[150]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[174]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[103]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[127]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[151]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[175]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[104]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[128]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[152]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[176]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[129]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[153]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[177]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[106]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[130]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[154]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[178]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[107]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[131]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[155]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[179]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[60]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[84]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[13]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[61]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[85]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[14]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[62]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[86]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[63]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[87]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[16]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[64]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[88]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[17]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[65]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[89]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[66]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[90]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[19]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[67]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[91]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[20]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[68]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[92]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[69]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[93]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[22]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[70]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[94]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[23]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[71]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[95]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[132]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[156]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[180]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[109]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[133]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[157]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[181]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[110]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[134]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[158]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[182]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[135]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[159]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[183]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[112]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[136]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[160]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[184]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[113]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[137]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[161]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[185]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[138]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[162]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[186]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[115]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[139]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[163]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[187]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[116]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[140]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[164]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[188]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[141]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[165]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[189]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[118]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[142]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[166]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[190]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[119]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[143]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[167]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[191]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(threadIdx.x_1*2)] = @tir.if_then_else(((7 <= floormod((threadIdx.x_1*2), 63)) && (floormod((threadIdx.x_1*2), 63) < 56)), data[(((cse_var_2 + (floordiv((threadIdx.x_1*2), 63)*49)) + floormod((threadIdx.x_1*2), 63)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else(((7 <= floormod(((threadIdx.x_1*2) + 1), 63)) && (floormod(((threadIdx.x_1*2) + 1), 63) < 56)), data[(((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 63)*49)) + floormod(((threadIdx.x_1*2) + 1), 63)) - 7)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 98), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 98), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 99), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 99), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*2) [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 196), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 196), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 197), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 197), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*2 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 294), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 294), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 295), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 295), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*2 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 392), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 393), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*2 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv((threadIdx.x_1*2), 7) + 7)*7) + floormod((threadIdx.x_1*2), 7)) + 441)] = @tir.if_then_else(((threadIdx.x_1*2) < 7), data[((cse_var_2 + (threadIdx.x_1*2)) + 385)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 2), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
}
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv(((threadIdx.x_1*2) + 1), 7) + 7)*7) + floormod(((threadIdx.x_1*2) + 1), 7)) + 441)] = @tir.if_then_else((((threadIdx.x_1*2) + 1) < 7), data[((cse_var_2 + ((threadIdx.x_1*2) + 1)) + 385)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 1), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
}
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 1), 24)*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 24)*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 45), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 24)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[0]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[48]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[72]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[1]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[49]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[73]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[2]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[50]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[74]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[51]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[75]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[4]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[52]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[76]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[5]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[53]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[77]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[54]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[78]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[7]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[55]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[79]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[8]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[56]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[80]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[57]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[81]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[10]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[58]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[82]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[11]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[59]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[83]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[96]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[120]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[144]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[168]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[97]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[121]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[145]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[169]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[98]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[122]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[146]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[170]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[123]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[147]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[171]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[100]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[124]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[148]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[172]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[101]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[125]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[149]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[173]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[126]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[150]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[174]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[103]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[127]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[151]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[175]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[104]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[128]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[152]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[176]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[129]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[153]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[177]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[106]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[130]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[154]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[178]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[107]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[131]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[155]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[179]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[60]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[84]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[13]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[61]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[85]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[14]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[62]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[86]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[63]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[87]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[16]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[64]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[88]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[17]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[65]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[89]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[66]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[90]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[19]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[67]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[91]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[20]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[68]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[92]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[69]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[93]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[22]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[70]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[94]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[23]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[71]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[95]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[132]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[156]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[180]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[109]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[133]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[157]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[181]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[110]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[134]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[158]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[182]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[135]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[159]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[183]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[112]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[136]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[160]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[184]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[113]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[137]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[161]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[185]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[138]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[162]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[186]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[115]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[139]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[163]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[187]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[116]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[140]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[164]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[188]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[141]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[165]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[189]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[118]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[142]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[166]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[190]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[119]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[143]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[167]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[191]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(threadIdx.x_1*2)] = @tir.if_then_else((((7 <= floormod((threadIdx.x_1*2), 63)) && (floormod((threadIdx.x_1*2), 63) < 56)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[(((cse_var_2 + (floordiv((threadIdx.x_1*2), 63)*49)) + floormod((threadIdx.x_1*2), 63)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else((((7 <= floormod(((threadIdx.x_1*2) + 1), 63)) && (floormod(((threadIdx.x_1*2) + 1), 63) < 56)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[(((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 63)*49)) + floormod(((threadIdx.x_1*2) + 1), 63)) - 6)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 98), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 98), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((thread [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 99), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 99), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1) [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 196), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 196), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((thre [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 197), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 197), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 294), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 294), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((thre [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 295), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 295), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 392), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((thre [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 393), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv((threadIdx.x_1*2), 7) + 7)*7) + floormod((threadIdx.x_1*2), 7)) + 441)] = @tir.if_then_else((((threadIdx.x_1*2) < 7) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((cse_var_2 + (threadIdx.x_1*2)) + 386)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 4), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 5), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 2), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 7), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 8), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 3), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 10), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 11), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 4), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 13), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 14), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 5), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 16), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 17), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 6), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 19), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 20), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 7), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 22), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 23), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
}
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv(((threadIdx.x_1*2) + 1), 7) + 7)*7) + floormod(((threadIdx.x_1*2) + 1), 7)) + 441)] = @tir.if_then_else(((((threadIdx.x_1*2) + 1) < 7) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((cse_var_2 + ((threadIdx.x_1*2) + 1)) + 386)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 8), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 25), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 26), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 9), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 28), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 29), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 10), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 31), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
}
}
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 1), 24)*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 24)*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 45), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 24)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ for (rc.outer.inner: int32, 0, 8) {
+ let cse_var_2: int32 = (rc.outer.inner*9)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_2]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 216)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 288)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 360)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 432)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 504)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 147)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 219)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 291)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 363)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 435)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 507)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 150)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 222)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 294)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 366)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 438)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 510)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 576)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 648)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 720)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 792)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 864)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 936)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1008)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1080)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 579)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 651)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 723)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 795)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 867)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 939)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1011)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1083)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 582)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 654)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 726)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 798)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 870)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 942)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1014)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1086)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 145)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 217)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 289)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 361)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 433)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 505)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 148)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 220)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 292)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 364)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 436)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 508)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 151)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 223)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 295)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 367)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 439)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 511)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 577)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 649)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 721)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 793)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 865)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 937)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1009)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1081)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 580)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 652)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 724)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 796)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 868)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 940)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1012)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1084)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 583)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 655)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 727)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 799)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 871)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 943)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1015)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1087)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 146)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 218)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 290)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 362)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 434)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 506)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 149)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 221)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 293)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 365)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 437)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 509)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 152)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 224)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 296)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 368)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 440)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 512)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 578)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 650)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 722)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 794)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 866)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 938)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1010)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1082)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 581)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 653)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 725)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 797)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 869)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 941)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1013)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1085)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 584)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 656)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 728)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 800)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 872)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 944)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1016)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1088)]))
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[0]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[48]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[72]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[1]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[49]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[73]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[2]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[50]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[74]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[51]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[75]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[4]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[52]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[76]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[5]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[53]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[77]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[54]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[78]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[7]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[55]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[79]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[8]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[56]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[80]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[57]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[81]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[10]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[58]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[82]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[11]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[59]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[83]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[96]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[120]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[144]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[168]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[97]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[121]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[145]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[169]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[98]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[122]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[146]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[170]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[123]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[147]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[171]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[100]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[124]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[148]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[172]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[101]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[125]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[149]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[173]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[126]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[150]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[174]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[103]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[127]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[151]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[175]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[104]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[128]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[152]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[176]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[129]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[153]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[177]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[106]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[130]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[154]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[178]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[107]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[131]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[155]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[179]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[60]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[84]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[13]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[61]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[85]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[14]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[62]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[86]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[63]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[87]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[16]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[64]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[88]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[17]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[65]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[89]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[66]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[90]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[19]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[67]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[91]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[20]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[68]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[92]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[69]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[93]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[22]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[70]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[94]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[23]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[71]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[95]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[132]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[156]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[180]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[109]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[133]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[157]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[181]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[110]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[134]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[158]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[182]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[135]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[159]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[183]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[112]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[136]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[160]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[184]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[113]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[137]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[161]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[185]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[138]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[162]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[186]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[115]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[139]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[163]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[187]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[116]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[140]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[164]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[188]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[141]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[165]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[189]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[118]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[142]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[166]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[190]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[119]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[143]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[167]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[191]))
}
}
- for (i1.inner: int32, 0, 8) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 16) {
+ compute[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*16) + i1.inner)]), 0f32)
}
}
}
@@ -1005,7 +599,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.241 ms
+ Execution time of this operator: 0.280 ms
@@ -1053,7 +647,7 @@ 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=4)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=8)
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_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
@@ -1065,17 +659,17 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=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)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=16)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
@@ -1100,16 +694,16 @@ 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=32)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1128,9 +722,9 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define uint64_t unsigned long long
#endif
extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[192];
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1139,658 +733,278 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = ((((7 <= ((((int)threadIdx.x) * 2) % 63)) && (((((int)threadIdx.x) * 2) % 63) < 56)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 63) * 49)) + ((((int)threadIdx.x) * 2) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = ((((7 <= (((((int)threadIdx.x) * 2) + 1) % 63)) && ((((((int)threadIdx.x) * 2) + 1) % 63) < 56)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 63) * 49)) + (((((int)threadIdx.x) * 2) + 1) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 98) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 98) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 8)] : 0.0000 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 99) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 99) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)t [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 196) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 196) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 8)] : 0.00 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 197) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 197) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 294) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 294) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 8)] : 0.00 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 295) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 295) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 392) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 392) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 8)] : 0.00 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 393) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 393) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int [...]
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 490)] = (((((int)threadIdx.x) < 4) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 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 * 392) + (((((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) + 441)] = (((((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 * 392) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((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 * 392) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 11) {
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = ((((((int)threadIdx.x) < 2) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 637) / 81) * 49)) + (((((int)threadIdx.x) + 70) / 9) * 7)) + ((int)threadIdx.x)) - 1)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 491)] = (((((int)threadIdx.x) < 3) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 385)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[(((int)threadIdx.x) * 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 1) % 24) * 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) % 24) * 3))];
- if (((int)threadIdx.x) < 45) {
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 1) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[0]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[48]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[72]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[1]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[49]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[73]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[2]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[50]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[74]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[3]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[51]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[75]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[4]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[52]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[76]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[5]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[53]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[77]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[6]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[54]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[78]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[7]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[55]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[79]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[8]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[56]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[80]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[9]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[57]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[81]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[10]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[58]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[82]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[11]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[59]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[83]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[96]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[120]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[144]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[168]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[97]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[121]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[145]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[169]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[98]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[122]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[146]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[170]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[99]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[123]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[147]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[171]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[100]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[124]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[148]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[172]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[101]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[125]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[149]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[173]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[102]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[126]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[150]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[174]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[103]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[127]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[151]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[175]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[104]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[128]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[152]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[176]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[105]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[129]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[153]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[177]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[106]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[130]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[154]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[178]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[107]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[131]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[155]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[179]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[12]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[60]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[84]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[13]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[61]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[85]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[14]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[62]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[86]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[15]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[63]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[87]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[16]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[64]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[88]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[17]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[65]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[89]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[18]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[66]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[90]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[19]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[67]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[91]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[20]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[68]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[92]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[21]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[69]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[93]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[22]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[70]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[94]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[23]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[71]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[95]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[108]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[132]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[156]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[180]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[109]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[133]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[157]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[181]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[110]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[134]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[158]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[182]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[111]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[135]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[159]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[183]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[112]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[136]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[160]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[184]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[113]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[137]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[161]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[185]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[114]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[138]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[162]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[186]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[115]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[139]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[163]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[187]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[116]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[140]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[164]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[188]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[117]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[141]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[165]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[189]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[118]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[142]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[166]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[190]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[119]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[143]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[167]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[191]));
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = (((7 <= ((((int)threadIdx.x) * 2) % 63)) && (((((int)threadIdx.x) * 2) % 63) < 56)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 63) * 49)) + ((((int)threadIdx.x) * 2) % 63)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((7 <= (((((int)threadIdx.x) * 2) + 1) % 63)) && ((((((int)threadIdx.x) * 2) + 1) % 63) < 56)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 63) * 49)) + (((((int)threadIdx.x) * 2) + 1) % 63)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 98) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 98) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 99) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 99) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 196) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 196) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 197) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 197) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 294) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 294) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 295) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 295) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 392) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 392) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 393) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 393) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 490)] = ((((int)threadIdx.x) < 4) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 385)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 2) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
}
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 491)] = ((((int)threadIdx.x) < 3) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 386)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 1) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 1)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 1) % 24) * 3)) + 1)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) % 24) * 3)) + 1)];
- if (((int)threadIdx.x) < 45) {
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 4) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[0]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[48]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[72]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[1]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[49]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[73]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[2]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[50]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[74]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[3]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[51]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[75]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[4]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[52]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[76]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[5]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[53]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[77]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[6]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[54]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[78]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[7]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[55]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[79]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[8]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[56]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[80]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[9]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[57]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[81]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[10]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[58]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[82]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[11]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[59]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[83]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[96]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[120]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[144]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[168]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[97]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[121]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[145]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[169]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[98]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[122]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[146]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[170]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[99]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[123]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[147]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[171]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[100]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[124]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[148]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[172]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[101]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[125]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[149]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[173]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[102]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[126]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[150]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[174]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[103]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[127]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[151]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[175]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[104]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[128]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[152]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[176]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[105]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[129]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[153]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[177]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[106]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[130]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[154]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[178]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[107]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[131]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[155]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[179]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[12]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[60]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[84]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[13]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[61]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[85]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[14]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[62]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[86]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[15]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[63]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[87]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[16]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[64]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[88]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[17]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[65]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[89]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[18]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[66]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[90]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[19]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[67]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[91]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[20]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[68]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[92]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[21]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[69]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[93]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[22]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[70]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[94]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[23]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[71]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[95]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[108]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[132]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[156]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[180]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[109]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[133]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[157]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[181]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[110]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[134]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[158]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[182]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[111]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[135]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[159]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[183]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[112]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[136]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[160]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[184]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[113]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[137]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[161]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[185]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[114]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[138]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[162]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[186]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[115]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[139]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[163]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[187]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[116]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[140]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[164]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[188]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[117]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[141]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[165]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[189]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[118]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[142]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[166]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[190]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[119]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[143]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[167]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[191]));
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = ((((7 <= ((((int)threadIdx.x) * 2) % 63)) && (((((int)threadIdx.x) * 2) % 63) < 56)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 63) * 49)) + ((((int)threadIdx.x) * 2) % 63)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = ((((7 <= (((((int)threadIdx.x) * 2) + 1) % 63)) && ((((((int)threadIdx.x) * 2) + 1) % 63) < 56)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 63) * 49)) + (((((int)threadIdx.x) * 2) + 1) % 63)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 98) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 98) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 6)] : 0.00000 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 99) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 99) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)th [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 196) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 196) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 6)] : 0.000 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 197) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 197) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int) [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 294) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 294) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 6)] : 0.000 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 295) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 295) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int) [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 392) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 392) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 6)] : 0.000 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 393) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 393) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int) [...]
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 490)] = (((((int)threadIdx.x) < 4) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 386)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 5) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 2) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 7) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 8) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 3) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 10) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 11) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 4) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
}
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 491)] = (((((int)threadIdx.x) < 3) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 387)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 13) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 2)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 1) % 24) * 3)) + 2)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) % 24) * 3)) + 2)];
- if (((int)threadIdx.x) < 45) {
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 14) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 5) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 16) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 17) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 6) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 19) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 20) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 7) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 22) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 23) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 8) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 25) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 26) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 9) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 28) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 29) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 10) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 31) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[0]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[48]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[72]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[1]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[49]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[73]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[2]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[50]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[74]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[3]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[51]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[75]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[4]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[52]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[76]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[5]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[53]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[77]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[6]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[54]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[78]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[7]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[55]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[79]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[8]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[56]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[80]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[9]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[57]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[81]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[10]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[58]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[82]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[11]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[59]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[83]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[96]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[120]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[144]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[168]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[97]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[121]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[145]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[169]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[98]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[122]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[146]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[170]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[99]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[123]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[147]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[171]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[100]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[124]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[148]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[172]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[101]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[125]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[149]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[173]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[102]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[126]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[150]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[174]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[103]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[127]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[151]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[175]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[104]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[128]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[152]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[176]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[105]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[129]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[153]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[177]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[106]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[130]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[154]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[178]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[107]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[131]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[155]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[179]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[12]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[60]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[84]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[13]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[61]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[85]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[14]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[62]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[86]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[15]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[63]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[87]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[16]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[64]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[88]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[17]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[65]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[89]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[18]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[66]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[90]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[19]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[67]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[91]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[20]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[68]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[92]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[21]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[69]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[93]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[22]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[70]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[94]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[23]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[71]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[95]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[108]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[132]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[156]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[180]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[109]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[133]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[157]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[181]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[110]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[134]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[158]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[182]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[111]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[135]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[159]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[183]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[112]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[136]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[160]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[184]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[113]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[137]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[161]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[185]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[114]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[138]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[162]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[186]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[115]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[139]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[163]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[187]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[116]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[140]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[164]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[188]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[117]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[141]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[165]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[189]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[118]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[142]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[166]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[190]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[119]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[143]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[167]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[191]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 216)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 288)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 360)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 432)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 504)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 219)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 291)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 363)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 435)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 507)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 222)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 294)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 366)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 438)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 510)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 576)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 648)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 720)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 792)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 864)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 936)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 1008)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 1080)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 579)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 651)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 723)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 795)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 867)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 939)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 1011)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 1083)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 582)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 654)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 726)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 798)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 870)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 942)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 1014)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 1086)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 217)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 289)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 361)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 433)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 505)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 220)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 292)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 364)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 436)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 508)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 223)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 295)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 367)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 439)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 511)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 577)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 649)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 721)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 793)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 865)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 937)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 1009)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 1081)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 580)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 652)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 724)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 796)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 868)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 940)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 1012)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 1084)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 583)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 655)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 727)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 799)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 871)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 943)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 1015)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 1087)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 218)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 290)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 362)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 434)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 506)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 221)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 293)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 365)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 437)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 509)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 224)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 296)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 368)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 440)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 512)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 578)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 650)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 722)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 794)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 866)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 938)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 1010)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 1082)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 581)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 653)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 725)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 797)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 869)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 941)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 1013)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 1085)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 584)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 656)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 728)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 800)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 872)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 944)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 1016)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 1088)]));
+ }
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1852,7 +1066,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 16.739 seconds)
+ **Total running time of the script:** ( 3 minutes 18.616 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 1156ebd94..cb1864118 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.0896 10.0922 10.1559 10.0207 0.0553
+ 10.0024 10.0123 10.0234 9.9716 0.0222
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 ce704fc3e..5d1ceb3b9 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 758.5364 758.4762 758.7755 758.3574 0.1759
+ 755.5098 755.0214 756.8228 754.6852 0.9385
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.099 seconds)
+ **Total running time of the script:** ( 1 minutes 22.138 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 c1e52d983..86c57ef05 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,121 +397,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), 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_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i.outer.inner*64) + (nb_j.inner*16))
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_2] = 0f32
- compute_5[(cse_var_2 + 1)] = 0f32
- compute_5[(cse_var_2 + 2)] = 0f32
- compute_5[(cse_var_2 + 3)] = 0f32
- compute_5[(cse_var_2 + 4)] = 0f32
- compute_5[(cse_var_2 + 5)] = 0f32
- compute_5[(cse_var_2 + 6)] = 0f32
- compute_5[(cse_var_2 + 7)] = 0f32
- compute_5[(cse_var_2 + 8)] = 0f32
- compute_5[(cse_var_2 + 9)] = 0f32
- compute_5[(cse_var_2 + 10)] = 0f32
- compute_5[(cse_var_2 + 11)] = 0f32
- compute_5[(cse_var_2 + 12)] = 0f32
- compute_5[(cse_var_2 + 13)] = 0f32
- compute_5[(cse_var_2 + 14)] = 0f32
- compute_5[(cse_var_2 + 15)] = 0f32
- compute_5[(cse_var_2 + 32)] = 0f32
- compute_5[(cse_var_2 + 33)] = 0f32
- compute_5[(cse_var_2 + 34)] = 0f32
- compute_5[(cse_var_2 + 35)] = 0f32
- compute_5[(cse_var_2 + 36)] = 0f32
- compute_5[(cse_var_2 + 37)] = 0f32
- compute_5[(cse_var_2 + 38)] = 0f32
- compute_5[(cse_var_2 + 39)] = 0f32
- compute_5[(cse_var_2 + 40)] = 0f32
- compute_5[(cse_var_2 + 41)] = 0f32
- compute_5[(cse_var_2 + 42)] = 0f32
- compute_5[(cse_var_2 + 43)] = 0f32
- compute_5[(cse_var_2 + 44)] = 0f32
- compute_5[(cse_var_2 + 45)] = 0f32
- compute_5[(cse_var_2 + 46)] = 0f32
- compute_5[(cse_var_2 + 47)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- let cse_var_35: int32 = (elem_idx*16)
- let cse_var_34: int32 = (cse_var_2 + 9)
- let cse_var_33: int32 = (cse_var_2 + 8)
- let cse_var_32: int32 = (cse_var_2 + 7)
- let cse_var_31: int32 = (cse_var_2 + 6)
- let cse_var_30: int32 = (cse_var_2 + 5)
- let cse_var_29: int32 = (cse_var_2 + 47)
- let cse_var_28: int32 = (cse_var_2 + 46)
- let cse_var_27: int32 = (cse_var_2 + 45)
- let cse_var_26: int32 = (cse_var_2 + 44)
- let cse_var_25: int32 = (cse_var_2 + 43)
- let cse_var_24: int32 = (cse_var_2 + 42)
- let cse_var_23: int32 = (cse_var_2 + 41)
- let cse_var_22: int32 = (cse_var_2 + 40)
- let cse_var_21: int32 = (cse_var_2 + 4)
- let cse_var_20: int32 = (cse_var_2 + 39)
- let cse_var_19: int32 = (cse_var_2 + 38)
- let cse_var_18: int32 = (cse_var_2 + 37)
- let cse_var_17: int32 = (cse_var_2 + 36)
- let cse_var_16: int32 = (cse_var_2 + 35)
- let cse_var_15: int32 = (cse_var_2 + 34)
- let cse_var_14: int32 = (cse_var_2 + 33)
- let cse_var_13: int32 = (cse_var_2 + 32)
- let cse_var_12: int32 = (cse_var_2 + 3)
- let cse_var_11: int32 = (cse_var_2 + 2)
- let cse_var_10: int32 = (cse_var_2 + 15)
- let cse_var_9: int32 = (cse_var_2 + 14)
- let cse_var_8: int32 = (cse_var_2 + 13)
- let cse_var_7: int32 = (cse_var_2 + 12)
- let cse_var_6: int32 = (cse_var_2 + 11)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*512))
- {
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_35)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- }
- }
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global;
+ for (i1.outer: int32, 0, 64) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [64], [])[((i.inner.init*16) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floordiv(i1.outer, 2) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floordiv(i1.outer, 2)
+ let cse_var_2: int32 = ((i.inner*16) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_36: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_36, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_36, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 4) {
+ for (i1.inner: int32, 0, 8) {
+ let cse_var_5: int32 = (i1.outer*8)
+ let cse_var_4: int32 = ((((i0.outer*2048) + (i0.inner*512)) + cse_var_5) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((((i0.inner*16) + cse_var_5) + i1.inner) - (floordiv(i1.outer, 2)*16))] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -567,7 +476,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 3.468 ms
+ Execution time of this operator: 2.553 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 0f6f595d7..76372d0c1 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
=================
-**00:46.801** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.141** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.766 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.106 | 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``) | 00:00.020 | 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 00d045144..c5d0ec98f 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 174.59/174.59 result: MeasureResult(costs=(0.0013259764777777778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0773606300354004, timestamp=1658799774.9398315) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/174.59 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 174.65/174.65 result: MeasureResult(costs=(0.0013254985555555556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0453152656555176, timestamp=1658801307.741073) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/174.65 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.67/260.67 result: MeasureResult(costs=(0.0008881046187845305,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7665858268737793, timestamp=1658799775.8549378) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.18/260.18 result: MeasureResult(costs=(0.0008897650828729283,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7439014911651611, timestamp=1658801308.6655772) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.48/260.67 result: MeasureResult(costs=(0.04222365825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8504853248596191, timestamp=1658799780.4401162) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.36/260.67 result: MeasureResult(costs=(0.068928888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.582594633102417, timestamp=1658799781.6768804) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.42/260.18 result: MeasureResult(costs=(0.042678113000000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8313236236572266, timestamp=1658801313.2114427) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/260.18 result: MeasureResult(costs=(0.0693738225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.546748638153076, timestamp=1658801314.4557946) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 26.08/260.67 result: MeasureResult(costs=(0.008878023,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1754045486450195, timestamp=1658799792.5894463) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.80/260.18 result: MeasureResult(costs=(0.008326810928571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2733991146087646, timestamp=1658801325.4546382) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001293
+ Time cost of this operator: 0.001299
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 5c7add586..f1abdc295 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.735 (1, 2, 10, 10, 3) 2 1 [311.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.024 0.958 (1, 6, 10, 10) 1 1 [3.024]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.308 (1, 1, 10, 10, 3) 1 1 [0.972]
- Total_time - 315.796 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.1 98.718 (1, 2, 10, 10, 3) 2 1 [309.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.046 0.973 (1, 6, 10, 10) 1 1 [3.046]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 0.309 (1, 1, 10, 10, 3) 1 1 [0.967]
+ Total_time - 313.113 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 151.9 98.219 (1, 6, 10, 10, 1) 2 1 [151.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.799 1.163 (1, 6, 10, 10) 1 1 [1.799]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.618 (1, 1, 10, 10, 3) 1 1 [0.955]
- Total_time - 154.654 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 89.75 97.054 (1, 6, 10, 10, 1) 2 1 [89.75]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.747 1.889 (1, 6, 10, 10) 1 1 [1.747]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.977 1.056 (1, 1, 10, 10, 3) 1 1 [0.977]
+ Total_time - 92.474 - - - - -
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 dac07da55..489260feb 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/tmp7ud5dzzs/images/random'
+ '/tmp/tmp5m0_tjya/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp7ud5dzzs/images/target contains 8144 images
- /tmp/tmp7ud5dzzs/images/random contains 5000 images
+ /tmp/tmp5m0_tjya/images/target contains 8144 images
+ /tmp/tmp5m0_tjya/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2132 - accuracy: 0.9247 - val_loss: 0.1246 - val_accuracy: 0.9615
+ 328/328 - 55s - loss: 0.2034 - accuracy: 0.9298 - val_loss: 0.1293 - val_accuracy: 0.9592
Epoch 2/3
- 328/328 - 53s - loss: 0.0995 - accuracy: 0.9636 - val_loss: 0.1065 - val_accuracy: 0.9641
+ 328/328 - 53s - loss: 0.0969 - accuracy: 0.9645 - val_loss: 0.1170 - val_accuracy: 0.9603
Epoch 3/3
- 328/328 - 52s - loss: 0.0642 - accuracy: 0.9764 - val_loss: 0.1033 - val_accuracy: 0.9675
+ 328/328 - 52s - loss: 0.0691 - accuracy: 0.9748 - val_loss: 0.0996 - val_accuracy: 0.9668
- <keras.callbacks.History object at 0x7fa987b33750>
+ <keras.callbacks.History object at 0x7fe791228f90>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 2.838 seconds)
+ **Total running time of the script:** ( 5 minutes 4.082 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 c29b7cd5e..58d9a9744 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**05:52.077** total execution time for **how_to_work_with_microtvm** files:
+**05:50.911** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:02.838 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:04.082 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:45.473 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.505 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.764 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.322 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 4af7810b3..cd760ae80 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:41.592** total execution time for **how_to_work_with_relay** files:
+**00:41.590** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.847 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.343 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.059 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.729 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.679 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.511 | 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 58120664e..3d2f78277 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 0x7fa9033e9e60>
+ <function my_cuda_math_rule at 0x7fe710e66710>
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 60cf311b7..c9e765ab4 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.235** total execution time for **how_to_work_with_schedules** files:
+**00:04.008** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.932 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.870 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.907 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.541 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.538 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.525 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.509 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.044 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.015 | 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 d0dd3e751..ef6f36070 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/tmpg15hcu9o/input0.cc'\nsource_filename = \"/tmp/tmpg15hcu9o/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/tmpjjc__28l/input0.cc'\nsource_filename = \"/tmp/tmpjjc__28l/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 d7ce3cabd..7b0821da4 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:21.680** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.388** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.673 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.382 | 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 354aad589..f23b3cd9a 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 23.51s!
+ resnet18_v1 inference graph built in 22.71s!
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 83c9d2736..d12636c60 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.31s!
+ yolov3-tiny inference graph built in 16.16s!
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 c295799dc..d62ba5a19 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:33.000** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.929** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.126 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.962 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.875 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.968 | 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 3bce575d5..a8ab9e31a 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
=================
-**00:03.332** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.192** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.926 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.801 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.406 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.391 | 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 d9c571290..dfd6f9770 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
=================
-**00:00.748** total execution time for **topic_vta_tutorials** files:
+**00:00.689** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.405 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.367 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.343 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.321 | 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 3dc3796fe..e8c17563a 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.910 ms
+ Execution time of this operator: 93.744 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 9d642415b..f7ed8338c 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.27/9.27 result: MeasureResult(costs=(0.0289464058,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5999782085418701, timestamp=1658798571.0366173) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.61/9.27 result: MeasureResult(costs=(0.10298805660000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.793806791305542, timestamp=1658798572.8589933) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0228047482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5762436389923096, timestamp=1658798573.9334927) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.72/11.77 result: MeasureResult(costs=(0.1561022328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621882438659668, timestamp=1658798577.130506) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.61/11.77 result: MeasureResult(costs=(0.07442361620000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3280863761901855, timestamp=1658798578.5874043) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.81/11.77 result: MeasureResult(costs=(0.1485806234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.540088176727295, timestamp=1658798581.171624) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.77 result: MeasureResult(costs=(0.30786764180000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.047713756561279, timestamp=1658798586.7968082) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.50/11.77 result: MeasureResult(costs=(0.025567515800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5525057315826416, timestamp=1658798587.3709717) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.89/11.77 result: MeasureResult(costs=(0.14188633820000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3703463077545166, timestamp=1658798589.8611484) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.50/11.77 result: MeasureResult(costs=(0.1072656572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8356046676635742, timestamp=1658798591.7556534) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.33/10.33 result: MeasureResult(costs=(0.025990367400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5508499145507812, timestamp=1658800125.9183948) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.94/10.33 result: MeasureResult(costs=(0.0912114386,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.611830472946167, timestamp=1658800128.0720844) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.82/11.82 result: MeasureResult(costs=(0.0227165708,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5627841949462891, timestamp=1658800129.1300826) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.88/11.82 result: MeasureResult(costs=(0.1431279612,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.407961130142212, timestamp=1658800131.5828235) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.67/11.82 result: MeasureResult(costs=(0.0732059746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3079211711883545, timestamp=1658800133.0200145) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.76/11.82 result: MeasureResult(costs=(0.152624874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.603809118270874, timestamp=1658800135.6682804) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.82 result: MeasureResult(costs=(0.3074617414,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.038850784301758, timestamp=1658800141.277615) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.76/11.82 result: MeasureResult(costs=(0.0249518638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5428321361541748, timestamp=1658800141.8420198) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.92/11.82 result: MeasureResult(costs=(0.13997261,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3405919075012207, timestamp=1658800144.302424) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.79/11.82 result: MeasureResult(costs=(0.0963210524,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6469123363494873, timestamp=1658800146.0075746) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 946ea37a5..93ef416b8 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 497.23278908998964, 'median': 497.44790824997835, 'std': 0.4699869257931475}
+ {'mean': 495.31586558001436, 'median': 495.21892269999626, 'std': 0.4674847601802359}
@@ -563,31 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 6.42 s
[Task 1/25] Current/Best: 6.07/ 17.42 GFLOPS | Progress: (8/20) | 9.43 s
[Task 1/25] Current/Best: 11.53/ 22.72 GFLOPS | Progress: (12/20) | 11.91 s
[Task 1/25] Current/Best: 16.67/ 22.79 GFLOPS | Progress: (16/20) | 13.61 s
[Task 1/25] Current/Best: 11.60/ 23.92 GFLOPS | Progress: (20/20) | 15.36 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.20/ 13.04 GFLOPS | Progress: (4/20) | 3.80 s
[Task 2/25] Current/Best: 14.10/ 18.52 GFLOPS | Progress: (8/20) | 5.10 s
[Task 2/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (12/20) | 6.43 s
[Task 2/25] Current/Best: 12.28/ 20.97 GFLOPS | Progress: (16/20) | 7.69 s
[Task 2/25] Current/Best: 19.70/ 20.97 GFLOPS | Progress: (20/20) | 9.33 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.57 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.52/ 16.89 GFLOPS | Progress: (8/20) | 7.81 s
[Task 3/25] Current/Best: 14.88/ 16.89 GFLOPS | Progress: (12/20) | 9.54 s
[Task 3/25] Current/Best: 7.20/ 23.74 GFLOPS | Progress: (16/20) | 11.46 s
[Task 3/25] Current/Best: 11.05/ 23.74 GFLOPS | Progress: (20/20) | 16.10 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.58/ 20.41 GFLOPS | Progress: (4/20) | 2.42 s
[Task 4/25] Current/Best: 6.51/ 20.41 GFLOPS | Progress: (8/20) | 7.22 s
[Task 4/25] Current/Best: 22.24/ 22.24 GFLOPS | Progress: (12/20) | 12.15 s
[Task 4/25] Current/Best: 16.68/ 22.24 GFLOPS | Progress: (16/20) | 14.59 s
[Task 4/25] Current/Best: 13.28/ 22.24 GFLOPS | Progress: (20/20) | 16.58 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.46/ 10.22 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.70/ 12.57 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 11.19/ 17.97 GFLOPS | Progress: (12/20) | 7.93 s
[Task 5/25] Current/Best: 11.69/ 22.95 GFLOPS | Progress: (16/20) | 9.38 s
[Task 5/25] Current/Best: 11.71/ 22.95 GFLOPS | Progress: (20/20) | 11.29 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.19/ 20.68 GFLOPS | Progress: (4/20) | 4.19 s
[Task 6/25] Current/Best: 18.96/ 20.68 GFLOPS | Progress: (8/20) | 5.96 s
[Task 6/25] Current/Best: 13.25/ 20.68 GFLOPS | Progress: (12/20) | 7.93 s
[Task 6/25] Current/Best: 19.97/ 20.68 GFLOPS | Progress: (16/20) | 10.21 s
[Task 6/25] Current/Best: 3.71/ 20.68 GFLOPS | Progress: (20/20) | 12.77 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.23/ 12.93 GFLOPS | Progress: (4/20) | 3.58 s
[Task 7/25] Current/Best: 20.21/ 20.94 GFLOPS | Progress: (8/20) | 5.09 s
[Task 7/25] Current/Best: 15.63/ 20.94 GFLOPS | Progress: (12/20) | 7.01 s
[Task 7/25] Current/Best: 12.21/ 20.94 GFLOPS | Progress: (16/20) | 9.07 s
[Task 7/25] Current/Best: 6.28/ 21.62 GFLOPS | Progress: (20/20) | 11.55 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.26/ 14.12 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.53/ 14.12 GFLOPS | Progress: (8/20) | 8.13 s
[Task 8/25] Current/Best: 13.01/ 14.12 GFLOPS | Progress: (12/20) | 14.76 s
[Task 8/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (16/20) | 16.89 s
[Task 8/25] Current/Best: 19.67/ 19.67 GFLOPS | Progress: (20/20) | 24.08 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.34/ 15.58 GFLOPS | Progress: (4/20) | 11.97 s
[Task 9/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 13.73 s
[Task 9/25] Current/Best: 8.24/ 23.46 GFLOPS | Progress: (12/20) | 16.27 s
[Task 9/25] Current/Best: 17.99/ 23.46 GFLOPS | Progress: (16/20) | 19.19 s
[Task 9/25] Current/Best: 9.17/ 23.46 GFLOPS | Progress: (20/20) | 28.00 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (4/20) | 2.58 s
[Task 10/25] Current/Best: 15.40/ 18.21 GFLOPS | Progress: (8/20) | 4.23 s
[Task 10/25] Current/Best: 12.49/ 18.70 GFLOPS | Progress: (12/20) | 5.78 s
[Task 10/25] Current/Best: 19.18/ 20.20 GFLOPS | Progress: (16/20) | 6.90 s
[Task 10/25] Current/Best: 8.89/ 20.20 GFLOPS | Progress: (20/20
) | 8.45 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.29/ 18.10 GFLOPS | Progress: (4/20) | 3.39 s
[Task 11/25] Current/Best: 16.98/ 18.10 GFLOPS | Progress: (8/20) | 6.21 s
[Task 11/25] Current/Best: 18.05/ 18.10 GFLOPS | Progress: (12/20) | 8.26 s
[Task 11/25] Current/Best: 13.48/ 21.10 GFLOPS | Progress: (16/20) | 11.18 s
[Task 11/25] Current/Best: 19.43/ 21.47 GFLOPS | Progress: (20/20) | 13.27 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.78/ 18.02 GFLOPS | Progress: (4/20) | 5.75 s
[Task 12/25] Current/Best: 5.21/ 18.02 GFLOPS | Progress: (8/20) | 9.75 s
[Task 12/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (12/20) | 11.79 s
[Task 12/25] Current/Best: 15.22/ 18.79 GFLOPS | Progress: (16/20) | 14.78 s
[Task 12/25] Current/Best: 15.09/ 18.79 GFLOPS | Progress: (20/20) | 16.71 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.73/ 17.29 GFLOPS | Progress: (4/20) | 3.80 s
[Task 13/25] Current/Best: 15.88/ 20.82 GFLOPS | Progress: (8/20) | 6.45 s
[Task 13/25] Current/Best: 19.44/ 21.61 GFLOPS | Progress: (12/20) | 9.47 s
[Task 13/25] Current/Best: 12.23/ 21.61 GFLOPS | Progress: (16/20) | 12.90 s
[Task 13/25] Current/Best: 18.66/ 21.61 GFLOPS | Progress: (20/20) | 15.24 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.59/ 13.59 GFLOPS | Progress: (4/20) | 3.45 s
[Task 14/25] Current/Best: 6.06/ 13.59 GFLOPS | Progress: (8/20) | 5.66 s
[Task 14/25] Current/Best: 20.10/ 20.10 GFLOPS | Progress: (12/20) | 8.33 s
[Task 14/25] Current/Best: 15.97/ 20.10 GFLOPS | Progress: (16/20) | 9.99 s Done.
-
[Task 14/25] Current/Best: 17.28/ 20.10 GFLOPS | Progress: (20/20) | 11.82 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.14/ 17.62 GFLOPS | Progress: (4/20) | 2.75 s
[Task 15/25] Current/Best: 14.32/ 17.98 GFLOPS | Progress: (8/20) | 4.09 s
[Task 15/25] Current/Best: 10.40/ 22.27 GFLOPS | Progress: (12/20) | 6.41 s
[Task 15/25] Current/Best: 20.38/ 22.27 GFLOPS | Progress: (16/20) | 9.89 s
[Task 15/25] Current/Best: 9.68/ 22.27 GFLOPS | Progress: (20/20) | 10.91 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (4/20) | 3.02 s
[Task 16/25] Current/Best: 3.04/ 20.58 GFLOPS | Progress: (8/20) | 4.69 s
[Task 16/25] Current/Best: 19.38/ 20.58 GFLOPS | Progress: (12/20) | 5.92 s
[Task 16/25] Current/Best: 17.17/ 20.58 GFLOPS | Progress: (16/20) |
7.30 s
[Task 16/25] Current/Best: 9.97/ 21.13 GFLOPS | Progress: (20/20) | 9.49 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.35/ 18.50 GFLOPS | Progress: (4/20) | 4.86 s
[Task 17/25] Current/Best: 13.17/ 23.21 GFLOPS | Progress: (8/20) | 7.80 s
[Task 17/25] Current/Best: 16.75/ 23.21 GFLOPS | Progress: (12/20) | 9.87 s
[Task 17/25] Current/Best: 16.42/ 23.21 GFLOPS | Progress: (16/20) | 12.10 s
[Task 17/25] Current/Best: 10.01/ 23.21 GFLOPS | Progress: (20/20) | 14.28 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.37/ 17.23 GFLOPS | Progress: (4/20) | 3.86 s
[Task 18/25] Current/Best: 10.56/ 20.09 GFLOPS | Progress: (8/20) | 7.61 s
[Task 18/25] Current/Best: 18.74/ 20.09 GFLOPS | Progress: (12/20) | 9.53 s
[Task 18/25] Current/Best: 9.96/ 20.09 GFLOPS | Progress: (16/20) | 13.48 s
[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.98 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.92/ 20.25 GFLOPS | Progress: (4/20) | 6.24 s
[Task 19/25] Current/Best: 2.60/ 20.25 GFLOPS | Progress: (8/20) | 9.60 s
[Task 19/25] Current/Best: 19.80/ 21.21 GFLOPS | Progress: (12/20) | 12.61 s
[Task 19/25] Current/Best: 15.02/ 21.36 GFLOPS | Progress: (16/20) | 15.66 s
[Task 19/25] Current/Best: 2.70/ 23.19 GFLOPS | Progress: (20/20) | 18.48 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.29/ 14.87 GFLOPS | Progress: (4/20) | 3.39 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.30/ 17.30 GFLOPS | Progress: (4/20) | 6.27 s
[Task 1/25] Current/Best: 6.14/ 17.30 GFLOPS | Progress: (8/20) | 9.28 s
[Task 1/25] Current/Best: 11.53/ 22.61 GFLOPS | Progress: (12/20) | 11.77 s
[Task 1/25] Current/Best: 16.80/ 22.73 GFLOPS | Progress: (16/20) | 13.46 s
[Task 1/25] Current/Best: 11.56/ 23.90 GFLOPS | Progress: (20/20) | 15.20 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.26/ 12.96 GFLOPS | Progress: (4/20) | 3.91 s
[Task 2/25] Current/Best: 14.18/ 18.66 GFLOPS | Progress: (8/20) | 5.19 s
[Task 2/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (12/20) | 6.51 s
[Task 2/25] Current/Best: 11.76/ 21.13 GFLOPS | Progress: (16/20) | 7.77 s
[Task 2/25] Current/Best: 19.35/ 21.13 GFLOPS | Progress: (20/20) | 9.41 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.58 GFLOPS | Progress: (4/20) | 5.87 s
[Task 3/25] Current/Best: 15.57/ 16.88 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 14.89/ 16.88 GFLOPS | Progress: (12/20) | 9.50 s
[Task 3/25] Current/Best: 7.21/ 23.76 GFLOPS | Progress: (16/20) | 11.41 s
[Task 3/25] Current/Best: 12.57/ 23.76 GFLOPS | Progress: (20/20) | 16.00 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.31 GFLOPS | Progress: (4/20) | 2.40 s
[Task 4/25] Current/Best: 6.87/ 20.31 GFLOPS | Progress: (8/20) | 7.16 s
[Task 4/25] Current/Best: 21.76/ 21.76 GFLOPS | Progress: (12/20) | 12.21 s
[Task 4/25] Current/Best: 16.82/ 21.76 GFLOPS | Progress: (16/20) | 14.64 s
[Task 4/25] Current/Best: 13.09/ 21.76 GFLOPS | Progress: (20/20) | 16.70 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.71/ 10.39 GFLOPS | Progress: (4/20) | 2.59 s
[Task 5/25] Current/Best: 11.85/ 12.72 GFLOPS | Progress: (8/20) | 4.65 s
[Task 5/25] Current/Best: 11.44/ 18.02 GFLOPS | Progress: (12/20) | 7.72 s
[Task 5/25] Current/Best: 11.80/ 22.58 GFLOPS | Progress: (16/20) | 9.13 s
[Task 5/25] Current/Best: 12.13/ 22.58 GFLOPS | Progress: (20/20) | 11.03 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.19/ 20.71 GFLOPS | Progress: (4/20) | 4.13 s
[Task 6/25] Current/Best: 18.95/ 20.71 GFLOPS | Progress: (8/20) | 5.88 s
[Task 6/25] Current/Best: 13.25/ 20.71 GFLOPS | Progress: (12/20) | 7.83 s
[Task 6/25] Current/Best: 19.96/ 20.71 GFLOPS | Progress: (16/20) | 10.08 s
[Task 6/25] Current/Best: 3.74/ 20.71 GFLOPS | Progress: (20/20) | 12.61 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.23/ 12.20 GFLOPS | Progress: (4/20) | 3.65 s
[Task 7/25] Current/Best: 20.31/ 21.15 GFLOPS | Progress: (8/20) | 5.18 s
[Task 7/25] Current/Best: 16.20/ 21.15 GFLOPS | Progress: (12/20) | 7.10 s
[Task 7/25] Current/Best: 12.24/ 21.15 GFLOPS | Progress: (16/20) | 9.15 s
[Task 7/25] Current/Best: 6.36/ 21.71 GFLOPS | Progress: (20/20) | 11.63 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.11/ 14.08 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.84/ 14.08 GFLOPS | Progress: (8/20) | 8.03 s
[Task 8/25] Current/Best: 12.57/ 14.08 GFLOPS | Progress: (12/20) | 14.56 s
[Task 8/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (16/20) | 16.67 s
[Task 8/25] Current/Best: 20.20/ 20.20 GFLOPS | Progress: (20/20) | 23.83 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.20/ 15.85 GFLOPS | Progress: (4/20) | 11.97 s
[Task 9/25] Current/Best: 23.40/ 23.40 GFLOPS | Progress: (8/20) | 13.71 s
[Task 9/25] Current/Best: 8.19/ 23.40 GFLOPS | Progress: (12/20) | 16.24 s
[Task 9/25] Current/Best: 17.98/ 23.40 GFLOPS | Progress: (16/20) | 19.03 s
[Task 9/25] Current/Best: 9.22/ 23.40 GFLOPS | Progress: (20/20) | 27.72 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (4/20) | 2.58 s
[Task 10/25] Current/Best: 15.52/ 18.26 GFLOPS | Progress: (8/20) | 4.21 s
[Task 10/25] Current/Best: 12.80/ 18.91 GFLOPS | Progress: (12/20) | 5.76 s
[Task 10/25] Current/Best: 19.18/ 20.31 GFLOPS | Progress: (16/20) | 6.86 s
[Task 10/25] Current/Best: 8.93/ 20.31 GFLOPS | Progress: (20/20
) | 8.38 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.28/ 18.07 GFLOPS | Progress: (4/20) | 3.33 s
[Task 11/25] Current/Best: 16.89/ 18.07 GFLOPS | Progress: (8/20) | 6.15 s
[Task 11/25] Current/Best: 18.10/ 18.10 GFLOPS | Progress: (12/20) | 8.20 s
[Task 11/25] Current/Best: 12.12/ 21.23 GFLOPS | Progress: (16/20) | 11.17 s
[Task 11/25] Current/Best: 19.45/ 21.23 GFLOPS | Progress: (20/20) | 13.30 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.77/ 18.06 GFLOPS | Progress: (4/20) | 5.82 s
[Task 12/25] Current/Best: 5.29/ 18.06 GFLOPS | Progress: (8/20) | 9.78 s
[Task 12/25] Current/Best: 18.34/ 18.87 GFLOPS | Progress: (12/20) | 11.76 s
[Task 12/25] Current/Best: 15.11/ 18.87 GFLOPS | Progress: (16/20) | 14.70 s
[Task 12/25] Current/Best: 15.08/ 18.99 GFLOPS | Progress: (20/20) | 16.67 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.68/ 17.27 GFLOPS | Progress: (4/20) | 3.76 s
[Task 13/25] Current/Best: 15.45/ 20.73 GFLOPS | Progress: (8/20) | 6.41 s
[Task 13/25] Current/Best: 19.32/ 21.47 GFLOPS | Progress: (12/20) | 9.46 s
[Task 13/25] Current/Best: 12.19/ 21.47 GFLOPS | Progress: (16/20) | 12.93 s
[Task 13/25] Current/Best: 18.40/ 21.47 GFLOPS | Progress: (20/20) | 15.30 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.59/ 13.59 GFLOPS | Progress: (4/20) | 3.41 s
[Task 14/25] Current/Best: 6.07/ 13.59 GFLOPS | Progress: (8/20) | 5.58 s
[Task 14/25] Current/Best: 19.23/ 19.23 GFLOPS | Progress: (12/20) | 8.27 s
[Task 14/25] Current/Best: 17.07/ 19.23 GFLOPS | Progress: (16/20) | 9.96 s Done.
+
[Task 14/25] Current/Best: 17.33/ 19.23 GFLOPS | Progress: (20/20) | 11.71 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.13/ 17.63 GFLOPS | Progress: (4/20) | 2.74 s
[Task 15/25] Current/Best: 14.37/ 18.07 GFLOPS | Progress: (8/20) | 4.08 s
[Task 15/25] Current/Best: 10.38/ 22.31 GFLOPS | Progress: (12/20) | 6.33 s
[Task 15/25] Current/Best: 20.42/ 22.31 GFLOPS | Progress: (16/20) | 9.99 s
[Task 15/25] Current/Best: 9.70/ 22.31 GFLOPS | Progress: (20/20) | 11.00 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (4/20) | 2.91 s
[Task 16/25] Current/Best: 3.00/ 20.64 GFLOPS | Progress: (8/20) | 4.52 s
[Task 16/25] Current/Best: 19.64/ 20.64 GFLOPS | Progress: (12/20) | 5.74 s
[Task 16/25] Current/Best: 18.06/ 20.64 GFLOPS | Progress: (16/20) |
7.13 s
[Task 16/25] Current/Best: 10.02/ 22.09 GFLOPS | Progress: (20/20) | 9.28 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.93/ 18.88 GFLOPS | Progress: (4/20) | 4.82 s
[Task 17/25] Current/Best: 14.17/ 23.34 GFLOPS | Progress: (8/20) | 7.73 s
[Task 17/25] Current/Best: 16.85/ 23.34 GFLOPS | Progress: (12/20) | 9.78 s
[Task 17/25] Current/Best: 16.47/ 23.34 GFLOPS | Progress: (16/20) | 12.02 s
[Task 17/25] Current/Best: 10.04/ 23.34 GFLOPS | Progress: (20/20) | 14.18 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.37/ 18.02 GFLOPS | Progress: (4/20) | 3.80 s
[Task 18/25] Current/Best: 10.60/ 19.91 GFLOPS | Progress: (8/20) | 7.53 s
[Task 18/25] Current/Best: 18.79/ 19.91 GFLOPS | Progress: (12/20) | 9.48 s
[Task 18/25] Current/Best: 10.03/ 19.91 GFLOPS | Progress: (16/20) | 13.33 s
[Task 18/25] Current/Best: 20.93/ 20.93 GFLOPS | Progress: (20/20) | 14.85 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.22/ 20.35 GFLOPS | Progress: (4/20) | 6.11 s
[Task 19/25] Current/Best: 2.59/ 20.35 GFLOPS | Progress: (8/20) | 9.42 s
[Task 19/25] Current/Best: 20.03/ 21.01 GFLOPS | Progress: (12/20) | 12.37 s
[Task 19/25] Current/Best: 13.53/ 21.01 GFLOPS | Progress: (16/20) | 15.43 s
[Task 19/25] Current/Best: 2.70/ 23.43 GFLOPS | Progress: (20/20) | 18.24 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.70/ 15.43 GFLOPS | Progress: (4/20) | 3.29 s Done.
Done.
-
[Task 20/25] Current/Best: 10.15/ 14.87 GFLOPS | Progress: (8/20) | 6.97 s
[Task 20/25] Current/Best: 2.32/ 16.57 GFLOPS | Progress: (12/20) | 10.96 s
[Task 20/25] Current/Best: 12.52/ 16.57 GFLOPS | Progress: (16/20) | 14.92 s
[Task 20/25] Current/Best: 13.14/ 21.48 GFLOPS | Progress: (20/20) | 17.06 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.53 GFLOPS | Progress: (4/20) | 3.32 s
[Task 21/25] Current/Best: 14.46/ 17.53 GFLOPS | Progress: (8/20) | 4.97 s
[Task 21/25] Current/Best: 1.61/ 17.53 GFLOPS | Progress: (12/20) | 7.15 s
[Task 21/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (16/20) | 10.71 s
[Task 21/25] Current/Best: 4.46/ 18.09 GFLOPS | Progress: (20/20) | 18.14 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.01 GFLOPS | Progress: (4/20
) | 2.72 s
[Task 22/25] Current/Best: 9.06/ 21.88 GFLOPS | Progress: (8/20) | 4.77 s
[Task 22/25] Current/Best: 19.94/ 21.88 GFLOPS | Progress: (12/20) | 7.16 s
[Task 22/25] Current/Best: 15.34/ 21.88 GFLOPS | Progress: (16/20) | 9.32 s
[Task 22/25] Current/Best: 14.61/ 21.88 GFLOPS | Progress: (20/20) | 11.07 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.32/ 20.34 GFLOPS | Progress: (4/20) | 3.30 s
[Task 23/25] Current/Best: 15.78/ 20.34 GFLOPS | Progress: (8/20) | 6.72 s
[Task 23/25] Current/Best: 20.74/ 21.43 GFLOPS | Progress: (12/20) | 8.59 s
[Task 23/25] Current/Best: 6.32/ 21.43 GFLOPS | Progress: (16/20) | 15.81 s
[Task 23/25] Current/Best: 7.58/ 21.43 GFLOPS | Progress: (20/20) | 20.08 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.67/ 8.67 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 3.32/ 8.67 GFLOPS | Progress: (8/20) | 23.11 s
[Task 24/25] Current/Best: 4.25/ 8.67 GFLOPS | Progress: (12/20) | 33.84 s Done.
- Done.
-
[Task 24/25] Current/Best: 6.75/ 8.67 GFLOPS | Progress: (16/20) | 39.68 s
[Task 24/25] Current/Best: 3.21/ 8.79 GFLOPS | Progress: (20/20) | 45.85 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.85 GFLOPS | Progress: (4/20) | 11.60 s
[Task 25/25] Current/Best: 5.65/ 7.55 GFLOPS | Progress: (8/20) | 22.88 s
[Task 25/25] Current/Best: 5.84/ 7.55 GFLOPS | Progress: (12/20) | 34.37 s
[Task 25/25] Current/Best: 5.65/ 8.79 GFLOPS | Progress: (16/20) | 36.16 s
[Task 25/25] Current/Best: 2.89/ 8.79 GFLOPS | Progress: (20/20) | 46.84 s
+
[Task 20/25] Current/Best: 10.60/ 15.43 GFLOPS | Progress: (8/20) | 6.81 s
[Task 20/25] Current/Best: 2.33/ 16.67 GFLOPS | Progress: (12/20) | 10.99 s
[Task 20/25] Current/Best: 12.43/ 16.67 GFLOPS | Progress: (16/20) | 14.94 s
[Task 20/25] Current/Best: 13.49/ 22.12 GFLOPS | Progress: (20/20) | 17.04 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.69 GFLOPS | Progress: (4/20) | 3.28 s
[Task 21/25] Current/Best: 14.61/ 17.69 GFLOPS | Progress: (8/20) | 4.82 s
[Task 21/25] Current/Best: 1.61/ 17.69 GFLOPS | Progress: (12/20) | 6.93 s
[Task 21/25] Current/Best: 16.28/ 17.69 GFLOPS | Progress: (16/20) | 10.47 s
[Task 21/25] Current/Best: 4.45/ 17.69 GFLOPS | Progress: (20/20) | 17.86 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.03 GFLOPS | Progress: (4/20
) | 2.69 s
[Task 22/25] Current/Best: 8.83/ 21.59 GFLOPS | Progress: (8/20) | 4.74 s
[Task 22/25] Current/Best: 19.86/ 21.59 GFLOPS | Progress: (12/20) | 7.12 s
[Task 22/25] Current/Best: 15.13/ 21.59 GFLOPS | Progress: (16/20) | 9.26 s
[Task 22/25] Current/Best: 14.29/ 21.59 GFLOPS | Progress: (20/20) | 11.01 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.09/ 20.46 GFLOPS | Progress: (4/20) | 3.27 s
[Task 23/25] Current/Best: 15.92/ 20.46 GFLOPS | Progress: (8/20) | 6.64 s
[Task 23/25] Current/Best: 20.82/ 21.52 GFLOPS | Progress: (12/20) | 8.50 s
[Task 23/25] Current/Best: 6.39/ 21.52 GFLOPS | Progress: (16/20) | 15.67 s
[Task 23/25] Current/Best: 7.65/ 21.52 GFLOPS | Progress: (20/20) | 19.92 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 2.13/ 8.58 GFLOPS | Progress: (8/20) | 22.89 s
[Task 24/25] Current/Best: 4.43/ 8.58 GFLOPS | Progress: (12/20) | 34.45 s Done.
+
[Task 24/25] Current/Best: 6.97/ 8.67 GFLOPS | Progress: (16/20) | 40.23 s
[Task 24/25] Current/Best: 3.26/ 8.75 GFLOPS | Progress: (20/20) | 46.22 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.92 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 5.61/ 7.84 GFLOPS | Progress: (8/20) | 22.90 s
[Task 25/25] Current/Best: 5.90/ 7.84 GFLOPS | Progress: (12/20) | 34.36 s
[Task 25/25] Current/Best: 5.74/ 9.23 GFLOPS | Progress: (16/20) | 36.22 s
[Task 25/25] Current/Best: 2.93/ 9.23 GFLOPS | Progress: (20/20) | 46.89 s
@@ -655,6 +654,7 @@ model using optimized operators to speed up our computations.
.. code-block:: none
+ Done.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 414.2256910499964, 'median': 413.89040999999906, 'std': 1.3894004535875637}
- unoptimized: {'mean': 497.23278908998964, 'median': 497.44790824997835, 'std': 0.4699869257931475}
+ optimized: {'mean': 407.31941859999097, 'median': 407.4516011000014, 'std': 0.8843930754312245}
+ unoptimized: {'mean': 495.31586558001436, 'median': 495.21892269999626, 'std': 0.4674847601802359}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 32.072 seconds)
+ **Total running time of the script:** ( 10 minutes 28.408 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 48f2ac554..584706b08 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.18e-07 secs/op
+ 1.211e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 5f0b1260f..05bca42fe 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, 0xc804570)), stage(b, placeholder(b, 0xdaee7b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+ [stage(a, placeholder(a, 0x2168ee90)), stage(b, placeholder(b, 0x1fe85880)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 7b6e8e8ec..41dc5dce5 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:18.347** total execution time for **tutorial** files:
+**13:16.875** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:32.072 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:28.408 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.352 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.239 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:49.882 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:55.077 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.348 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.237 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.306 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.559 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.703 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.695 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.514 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.502 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.163 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.152 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_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 21df392bc..f46a4501d 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,8 +301,8 @@ 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: 0.000006
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000007
+ parallel: 0.000006
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000025
+ vector: 0.000026
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.20454999939102e-06 1.0
- naive 6.8339e-06 0.8329402588206841
- parallel 6.957199999999999e-06 0.8479685053435466
- vector 2.48402e-05 3.0276127273090854
+ numpy 7.0601300012640425e-06 1.0
+ naive 5.84e-06 0.8271802359098783
+ parallel 6.0257e-06 0.8534828677263961
+ vector 2.59548e-05 3.6762495868139915
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018785
+ Numpy running time: 0.018889
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.364164
+ none: 3.190615
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.298375
+ blocking: 0.313139
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.340625
+ vectorization: 0.342124
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.119436
+ loop permutation: 0.117398
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.110504
+ array packing: 0.110086
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111076
+ block caching: 0.110578
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.144987
+ parallelization: 0.145305
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3641640066000003 1.0
- blocking 0.2983750644 0.08869218736501298
- vectorization 0.3406251059 0.10125104044622768
- loop permutation 0.1194358432 0.035502384237416564
- array packing 0.1105040509 0.03284740300508748
- block caching 0.11107618440000003 0.03301747007044981
- parallelization 0.1449874617 0.043097619918516364
+ none 3.1906150909 1.0
+ blocking 0.3131393966 0.09814389629545395
+ vectorization 0.34212372430000004 0.10722814082957738
+ loop permutation 0.11739830479999999 0.036794881693762875
+ array packing 0.1100858576 0.03450302040944315
+ block caching 0.11057846 0.03465741145504591
+ parallelization 0.1453047988 0.04554131246179645
@@ -1686,11 +1686,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.352 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 065b78885..1bc5100eb 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-ca2ec5429b4f9bf0864b1935d9046e6ec9235232
+9963b59ffa489db61358dedd35a2453a5ca666b9
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 2618d88b0..6862f3260 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -569,7 +569,7 @@ 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 3.804 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.256 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index c39c49f09..5739d0373 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe79293e5-13ee-446d-b6dc-eb566eab2105 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.zip241cd94a-0a75-467f-90bb-913710ef9eef 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 55dfbc551..4bf29e6dd 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,14 +427,13 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 58.6MB/s]
- 29%|##8 | 11.9M/41.5M [00:00<00:00, 44.7MB/s]
- 39%|###9 | 16.3M/41.5M [00:00<00:01, 24.4MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 32.8MB/s]
- 64%|######3 | 26.4M/41.5M [00:00<00:00, 27.8MB/s]
- 77%|#######7 | 32.0M/41.5M [00:01<00:00, 33.6MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 37.8MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 34.8MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 64.9MB/s]
+ 30%|### | 12.5M/41.5M [00:00<00:00, 62.6MB/s]
+ 45%|####4 | 18.5M/41.5M [00:00<00:00, 32.1MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.7MB/s]
+ 80%|######## | 33.4M/41.5M [00:00<00:00, 48.9MB/s]
+ 95%|#########4| 39.2M/41.5M [00:00<00:00, 51.7MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 43.8MB/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 9224224ec..83a367546 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,10 +409,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 8%|7 | 3.45M/44.7M [00:00<00:01, 36.1MB/s]
- 17%|#6 | 7.40M/44.7M [00:00<00:00, 39.2MB/s]
- 73%|#######2 | 32.4M/44.7M [00:00<00:00, 141MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 134MB/s]
+ 43%|####2 | 19.1M/44.7M [00:00<00:00, 199MB/s]
+ 98%|#########8| 43.8M/44.7M [00:00<00:00, 235MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 231MB/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 acc22e81c..47eeb1d61 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.897 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.235 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 904f853be..fce23183f 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:07.112</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>04:59.514</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,43 +331,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_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>01:03.804</p></td>
+<td><p>01:02.256</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>01:02.897</p></td>
+<td><p>01:02.235</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:40.109</p></td>
+<td><p>00:38.737</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:28.942</p></td>
+<td><p>00:27.344</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>00:25.609</p></td>
+<td><p>00:25.382</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.537</p></td>
+<td><p>00:24.472</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.512</p></td>
+<td><p>00:21.892</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>00:20.197</p></td>
+<td><p>00:19.800</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:15.109</p></td>
+<td><p>00:14.626</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>00:02.397</p></td>
+<td><p>00:02.769</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 af6d9c5d2..7dd99cd31 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0137 16.0081 16.1106 15.9247 0.0619
+ 15.8462 15.8432 16.0139 15.6569 0.0882
</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 3d67bd391..24e2dea34 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,45 +431,15 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|2 | 4.56M/170M [00:00<00:03, 46.5MB/s]
- 5%|5 | 9.00M/170M [00:00<00:03, 42.5MB/s]
- 8%|7 | 13.1M/170M [00:00<00:04, 38.4MB/s]
- 10%|9 | 16.8M/170M [00:00<00:04, 33.3MB/s]
- 12%|#1 | 20.0M/170M [00:00<00:05, 31.2MB/s]
- 15%|#4 | 25.1M/170M [00:00<00:04, 37.4MB/s]
- 18%|#7 | 30.1M/170M [00:00<00:03, 41.6MB/s]
- 20%|## | 34.2M/170M [00:01<00:04, 31.7MB/s]
- 23%|##2 | 38.4M/170M [00:01<00:03, 34.6MB/s]
- 26%|##5 | 43.7M/170M [00:01<00:03, 39.9MB/s]
- 29%|##8 | 48.5M/170M [00:01<00:03, 41.5MB/s]
- 31%|###1 | 52.8M/170M [00:01<00:03, 38.7MB/s]
- 33%|###3 | 56.7M/170M [00:01<00:03, 39.2MB/s]
- 36%|###6 | 61.2M/170M [00:01<00:02, 41.4MB/s]
- 39%|###8 | 65.9M/170M [00:01<00:02, 43.3MB/s]
- 41%|####1 | 70.1M/170M [00:01<00:02, 40.2MB/s]
- 44%|####3 | 74.4M/170M [00:02<00:02, 41.4MB/s]
- 46%|####6 | 78.6M/170M [00:02<00:02, 42.0MB/s]
- 49%|####8 | 82.6M/170M [00:02<00:02, 39.7MB/s]
- 51%|#####1 | 86.6M/170M [00:02<00:02, 40.2MB/s]
- 53%|#####3 | 90.5M/170M [00:02<00:02, 37.8MB/s]
- 57%|#####6 | 96.3M/170M [00:02<00:01, 44.0MB/s]
- 59%|#####9 | 101M/170M [00:02<00:01, 42.3MB/s]
- 62%|######2 | 105M/170M [00:02<00:01, 44.4MB/s]
- 65%|######4 | 110M/170M [00:02<00:01, 41.4MB/s]
- 68%|######7 | 115M/170M [00:03<00:01, 45.3MB/s]
- 71%|####### | 120M/170M [00:03<00:01, 46.7MB/s]
- 73%|#######3 | 124M/170M [00:03<00:01, 41.6MB/s]
- 76%|#######5 | 129M/170M [00:03<00:00, 43.6MB/s]
- 79%|#######8 | 133M/170M [00:03<00:00, 41.5MB/s]
- 81%|########1 | 138M/170M [00:03<00:00, 42.4MB/s]
- 84%|########4 | 143M/170M [00:03<00:00, 45.5MB/s]
- 87%|########6 | 147M/170M [00:03<00:00, 45.2MB/s]
- 89%|########9 | 152M/170M [00:03<00:00, 42.4MB/s]
- 92%|#########1| 156M/170M [00:04<00:00, 41.8MB/s]
- 94%|#########4| 160M/170M [00:04<00:00, 38.0MB/s]
- 96%|#########6| 163M/170M [00:04<00:00, 37.0MB/s]
- 98%|#########8| 167M/170M [00:04<00:00, 35.2MB/s]
-100%|##########| 170M/170M [00:04<00:00, 39.6MB/s]
+ 10%|9 | 16.8M/170M [00:00<00:00, 176MB/s]
+ 21%|##1 | 36.1M/170M [00:00<00:00, 192MB/s]
+ 32%|###2 | 54.6M/170M [00:00<00:00, 192MB/s]
+ 43%|####2 | 72.9M/170M [00:00<00:00, 185MB/s]
+ 57%|#####6 | 96.5M/170M [00:00<00:00, 207MB/s]
+ 70%|####### | 119M/170M [00:00<00:00, 218MB/s]
+ 83%|########2 | 140M/170M [00:00<00:00, 189MB/s]
+ 94%|#########3| 159M/170M [00:00<00:00, 192MB/s]
+100%|##########| 170M/170M [00:00<00:00, 196MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -564,7 +534,7 @@ 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 5.150 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 58.525 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 f264e2379..442cf42bb 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -475,14 +475,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 4%|3 | 528k/13.6M [00:00<00:02, 5.38MB/s]
- 12%|#1 | 1.59M/13.6M [00:00<00:01, 8.85MB/s]
- 21%|##1 | 2.86M/13.6M [00:00<00:01, 10.9MB/s]
- 33%|###2 | 4.46M/13.6M [00:00<00:00, 13.2MB/s]
- 47%|####7 | 6.41M/13.6M [00:00<00:00, 15.8MB/s]
- 65%|######5 | 8.84M/13.6M [00:00<00:00, 19.0MB/s]
- 87%|########6 | 11.7M/13.6M [00:00<00:00, 22.7MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 18.8MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 157MB/s]
</pre></div>
</div>
</div>
@@ -571,7 +564,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4538 90.2867 101.4936 90.1615 1.1237
+ 90.2781 90.2287 91.5704 89.9942 0.2159
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +603,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.329 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.453 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 db81406a2..18d7bcf44 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -568,7 +568,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.6525 119.5073 123.2438 118.9992 0.6467
+ 120.2829 120.1988 126.0842 119.5414 0.6776
</pre></div>
</div>
<div class="admonition note">
@@ -596,7 +596,7 @@ 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 3.537 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 57.067 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 502ab1883..7be60b34e 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.584 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.339 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 79bf1ee38..ccf09d2de 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,24 +436,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|3 | 4365/132723 [00:00<00:02, 43639.95KB/s]
- 9%|8 | 11901/132723 [00:00<00:01, 62290.78KB/s]
- 14%|#3 | 18131/132723 [00:00<00:02, 50855.93KB/s]
- 20%|## | 26660/132723 [00:00<00:01, 62817.80KB/s]
- 25%|##5 | 33229/132723 [00:00<00:01, 50168.26KB/s]
- 31%|###1 | 41601/132723 [00:00<00:01, 59276.56KB/s]
- 37%|###7 | 49140/132723 [00:00<00:01, 59984.19KB/s]
- 43%|####3 | 57153/132723 [00:00<00:01, 65480.59KB/s]
- 49%|####9 | 65523/132723 [00:01<00:01, 61634.85KB/s]
- 55%|#####4 | 72814/132723 [00:01<00:00, 64555.58KB/s]
- 61%|######1 | 81357/132723 [00:01<00:00, 70194.05KB/s]
- 67%|######6 | 88633/132723 [00:01<00:00, 61920.36KB/s]
- 73%|#######3 | 97136/132723 [00:01<00:00, 67877.13KB/s]
- 80%|#######9 | 105644/132723 [00:01<00:00, 72507.04KB/s]
- 86%|########6 | 114235/132723 [00:01<00:00, 76223.83KB/s]
- 92%|#########2| 122518/132723 [00:01<00:00, 78097.99KB/s]
- 99%|#########8| 131023/132723 [00:01<00:00, 80103.50KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 67048.15KB/s]
+ 4%|3 | 4856/132723 [00:00<00:02, 47656.08KB/s]
+ 8%|8 | 10687/132723 [00:00<00:02, 53870.66KB/s]
+ 15%|#4 | 19272/132723 [00:00<00:01, 68408.18KB/s]
+ 21%|##1 | 27923/132723 [00:00<00:01, 75532.91KB/s]
+ 28%|##7 | 36551/132723 [00:00<00:01, 79400.35KB/s]
+ 34%|###4 | 45265/132723 [00:00<00:01, 82027.29KB/s]
+ 40%|#### | 53565/132723 [00:00<00:00, 82340.52KB/s]
+ 47%|####6 | 61969/132723 [00:00<00:00, 82878.94KB/s]
+ 53%|#####2 | 70259/132723 [00:00<00:00, 77624.42KB/s]
+ 60%|#####9 | 78975/132723 [00:01<00:00, 80433.90KB/s]
+ 66%|######5 | 87077/132723 [00:01<00:00, 70062.47KB/s]
+ 72%|#######2 | 95777/132723 [00:01<00:00, 74617.15KB/s]
+ 78%|#######7 | 103480/132723 [00:01<00:00, 71229.01KB/s]
+ 84%|########4 | 112086/132723 [00:01<00:00, 75273.48KB/s]
+ 90%|######### | 119784/132723 [00:01<00:00, 42716.31KB/s]
+ 97%|#########6| 128470/132723 [00:01<00:00, 50850.70KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 65178.89KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -496,7 +495,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 34.802 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 32.562 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 11aea47b7..10a9e075d 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:17.478</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:00.195</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:05.150</p></td>
+<td><p>02:58.525</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:34.802</p></td>
+<td><p>02:32.562</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>02:03.537</p></td>
+<td><p>01:57.067</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>01:30.584</p></td>
+<td><p>01:31.339</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:10.329</p></td>
+<td><p>01:08.453</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.945</p></td>
+<td><p>00:29.483</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:23.125</p></td>
+<td><p>00:22.760</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index cfd76d890..f5ac90a66 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -607,7 +607,7 @@ 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.zipa09fc72a-76bb-4028-ba1b-cfa89ad94b70 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.zip1b5687ac-8be1-4d2a-8e84-6db2dd5730f0 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 73b4a5ee5..32b540324 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.145</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.169</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.878</p></td>
+<td><p>00:37.007</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>00:02.310</p></td>
+<td><p>00:02.226</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.949</p></td>
+<td><p>00:00.928</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 c9ad6c653..389afefbe 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6775us [6775us] (46.02%; 46.02%)
-FoldScaleAxis: 7947us [6us] (53.98%; 53.98%)
- FoldConstant: 7941us [1643us] (53.94%; 99.92%)
- InferType: 6298us [6298us] (42.78%; 79.31%)
+InferType: 6742us [6742us] (45.85%; 45.85%)
+FoldScaleAxis: 7963us [6us] (54.15%; 54.15%)
+ FoldConstant: 7957us [1608us] (54.11%; 99.93%)
+ InferType: 6349us [6349us] (43.18%; 79.79%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6291us [6291us] (44.54%; 44.54%)
-FoldScaleAxis: 7834us [5us] (55.46%; 55.46%)
- FoldConstant: 7829us [1650us] (55.43%; 99.94%)
- InferType: 6179us [6179us] (43.75%; 78.92%)
+InferType: 6549us [6549us] (45.16%; 45.16%)
+FoldScaleAxis: 7952us [5us] (54.84%; 54.84%)
+ FoldConstant: 7946us [1654us] (54.80%; 99.93%)
+ InferType: 6292us [6292us] (43.39%; 79.18%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 4c88c90ed..843208e94 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -559,7 +559,7 @@ 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: 37.951357 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 33.218063 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 6206e83d1..eeceafe0d 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -901,7 +901,7 @@ 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: 11.651502 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.231977 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 63c07521e..81702227c 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -456,8 +456,8 @@ 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: 0.019570
-Baseline: 3.356191
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019313
+Baseline: 3.259689
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -517,7 +517,7 @@ 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: 0.313325
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.298590
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -584,7 +584,7 @@ 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: 0.346535
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337184
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -645,7 +645,7 @@ 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: 0.116763
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.119793
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -728,7 +728,7 @@ 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: 0.110824
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111383
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -814,7 +814,7 @@ 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: 0.111837
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111500
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -904,7 +904,7 @@ 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: 0.145436
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144905
</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 aad1d2241..218da36e4 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.741</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.015</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.451</p></td>
+<td><p>00:31.846</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>00:01.289</p></td>
+<td><p>00:01.224</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>00:01.001</p></td>
+<td><p>00:00.945</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 495c38653..b222a4a22 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:03.618</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:02.992</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:16.739</p></td>
+<td><p>03:18.616</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>01:23.099</p></td>
+<td><p>01:22.138</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:46.419</p></td>
+<td><p>00:45.693</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>00:19.342</p></td>
+<td><p>00:18.736</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.099</p></td>
+<td><p>00:09.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.920</p></td>
+<td><p>00:08.785</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 5106b5555..f6a6f031f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -486,12 +486,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [192]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=64)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -499,704 +499,298 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[15] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (rc.outer.outer*392)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[(threadIdx.x_1*2)] = @tir.if_then_else((((7 <= floormod((threadIdx.x_1*2), 63)) && (floormod((threadIdx.x_1*2), 63) < 56)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[(((cse_var_2 + (floordiv((threadIdx.x_1*2), 63)*49)) + floormod((threadIdx.x_1*2), 63)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else((((7 <= floormod(((threadIdx.x_1*2) + 1), 63)) && (floormod(((threadIdx.x_1*2) + 1), 63) < 56)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[(((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 63)*49)) + floormod(((threadIdx.x_1*2) + 1), 63)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 49)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 49), 81)) && (floormod((threadIdx.x_1 + 49), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 49), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 8), 9)) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 147)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 66), 81)) && (floormod((threadIdx.x_1 + 66), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 147), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 66), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 245)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 2), 81)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 245), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 2), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 343)] = @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 + 343), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 19), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 441)] = @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 + 441), 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @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 + 490), 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 539)] = @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 + 539), 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" = 49;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @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 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
+ if @tir.likely((threadIdx.x_1 < 11), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 637)] = @tir.if_then_else((((threadIdx.x_1 < 2) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 637), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 70), 81), 9)*7)) + (threadIdx.x_1 + 7)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 98), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 98), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)* [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 99), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 99), 63)*49)) + (floormod((floordiv(( [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 196), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 196), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9 [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 197), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 197), 63)*49)) + (floormod((floordiv [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 294), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 294), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9 [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 295), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 295), 63)*49)) + (floormod((floordiv [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 392), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9) < 8)) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9 [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 393), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9) < 8)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 63)*49)) + (floormod((floordiv [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv((threadIdx.x_1*2), 7) + 7)*7) + floormod((threadIdx.x_1*2), 7)) + 441)] = @tir.if_then_else((((threadIdx.x_1*2) < 7) && (1 <= floormod((threadIdx.x_1*2), 7))), data[((cse_var_2 + (threadIdx.x_1*2)) + 384)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[(threadIdx.x_2*32)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod((threadIdx.x_2*32), 72), 3)*3)) + floormod((threadIdx.x_2*2), 3))]
}
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv(((threadIdx.x_1*2) + 1), 7) + 7)*7) + floormod(((threadIdx.x_1*2) + 1), 7)) + 441)] = @tir.if_then_else(((((threadIdx.x_1*2) + 1) < 7) && (1 <= floormod(((threadIdx.x_1*2) + 1), 7))), data[((cse_var_2 + ((threadIdx.x_1*2) + 1)) + 384)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 1), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
}
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [192], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 1), 24)*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 24)*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 45), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 24)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3))]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[0]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[48]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[72]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[1]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[49]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[73]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[2]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[50]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[74]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[51]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[75]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[4]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[52]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[76]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[5]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[53]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[77]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[54]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[78]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[7]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[55]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[79]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[8]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[56]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[80]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[57]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[81]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[10]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[58]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[82]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[11]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[59]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[83]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[96]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[120]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[144]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[168]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[97]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[121]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[145]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[169]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[98]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[122]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[146]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[170]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[123]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[147]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[171]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[100]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[124]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[148]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[172]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[101]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[125]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[149]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[173]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[126]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[150]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[174]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[103]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[127]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[151]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[175]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[104]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[128]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[152]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[176]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[129]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[153]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[177]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[106]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[130]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[154]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[178]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[107]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[131]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[155]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[179]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[60]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[84]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[13]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[61]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[85]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[14]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[62]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[86]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[63]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[87]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[16]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[64]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[88]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[17]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[65]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[89]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[66]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[90]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[19]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[67]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[91]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[20]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[68]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[92]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[69]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[93]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[22]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[70]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[94]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[23]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[71]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[95]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[132]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[156]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[180]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[109]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[133]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[157]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[181]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[110]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[134]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[158]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[182]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[135]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[159]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[183]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[112]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[136]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[160]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[184]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[113]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[137]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[161]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[185]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[138]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[162]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[186]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[115]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[139]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[163]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[187]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[116]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[140]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[164]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[188]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[141]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[165]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[189]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[118]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[142]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[166]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[190]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[119]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[143]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[167]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[191]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(threadIdx.x_1*2)] = @tir.if_then_else(((7 <= floormod((threadIdx.x_1*2), 63)) && (floormod((threadIdx.x_1*2), 63) < 56)), data[(((cse_var_2 + (floordiv((threadIdx.x_1*2), 63)*49)) + floormod((threadIdx.x_1*2), 63)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else(((7 <= floormod(((threadIdx.x_1*2) + 1), 63)) && (floormod(((threadIdx.x_1*2) + 1), 63) < 56)), data[(((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 63)*49)) + floormod(((threadIdx.x_1*2) + 1), 63)) - 7)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 98), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 98), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, dty [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 99), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 99), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadI [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 196), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 196), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, d [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 197), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 197), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threa [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 294), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 294), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, d [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 295), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 295), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threa [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 392), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else(((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7)) - 7)], 0f32, d [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 393), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else(((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 63)*49)) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threa [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv((threadIdx.x_1*2), 7) + 7)*7) + floormod((threadIdx.x_1*2), 7)) + 441)] = @tir.if_then_else(((threadIdx.x_1*2) < 7), data[((cse_var_2 + (threadIdx.x_1*2)) + 385)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 2), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
}
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv(((threadIdx.x_1*2) + 1), 7) + 7)*7) + floormod(((threadIdx.x_1*2) + 1), 7)) + 441)] = @tir.if_then_else((((threadIdx.x_1*2) + 1) < 7), data[((cse_var_2 + ((threadIdx.x_1*2) + 1)) + 385)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 1), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
}
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 1), 24)*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 24)*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 45), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 24)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 1)]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[0]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[48]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[72]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[1]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[49]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[73]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[2]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[50]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[74]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[51]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[75]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[4]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[52]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[76]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[5]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[53]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[77]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[54]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[78]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[7]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[55]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[79]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[8]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[56]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[80]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[57]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[81]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[10]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[58]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[82]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[11]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[59]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[83]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[96]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[120]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[144]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[168]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[97]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[121]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[145]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[169]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[98]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[122]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[146]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[170]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[123]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[147]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[171]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[100]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[124]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[148]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[172]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[101]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[125]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[149]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[173]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[126]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[150]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[174]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[103]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[127]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[151]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[175]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[104]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[128]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[152]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[176]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[129]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[153]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[177]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[106]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[130]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[154]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[178]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[107]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[131]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[155]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[179]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[60]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[84]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[13]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[61]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[85]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[14]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[62]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[86]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[63]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[87]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[16]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[64]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[88]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[17]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[65]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[89]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[66]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[90]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[19]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[67]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[91]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[20]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[68]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[92]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[69]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[93]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[22]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[70]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[94]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[23]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[71]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[95]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[132]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[156]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[180]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[109]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[133]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[157]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[181]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[110]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[134]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[158]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[182]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[135]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[159]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[183]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[112]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[136]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[160]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[184]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[113]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[137]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[161]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[185]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[138]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[162]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[186]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[115]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[139]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[163]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[187]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[116]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[140]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[164]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[188]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[141]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[165]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[189]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[118]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[142]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[166]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[190]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[119]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[143]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[167]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[191]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(threadIdx.x_1*2)] = @tir.if_then_else((((7 <= floormod((threadIdx.x_1*2), 63)) && (floormod((threadIdx.x_1*2), 63) < 56)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[(((cse_var_2 + (floordiv((threadIdx.x_1*2), 63)*49)) + floormod((threadIdx.x_1*2), 63)) - 6)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else((((7 <= floormod(((threadIdx.x_1*2) + 1), 63)) && (floormod(((threadIdx.x_1*2) + 1), 63) < 56)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[(((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 63)*49)) + floormod(((threadIdx.x_1*2) + 1), 63)) - 6)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 98), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 98), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 5), 9)*7 [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 99), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 5), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 99), 63)*49)) + (floormod((floordiv((( [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 196), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 196), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 1), 9) [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 197), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 1), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 197), 63)*49)) + (floormod((floordiv( [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 294), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 294), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 6), 9) [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 295), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 6), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 295), 63)*49)) + (floormod((floordiv( [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 392), 63)*63) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*2), 7))] = @tir.if_then_else((((1 <= floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9) < 8)) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 392), 63)*49)) + (floormod((floordiv((threadIdx.x_1*2), 7) + 2), 9) [...]
- pad_temp.shared_1[(((floordiv(((threadIdx.x_1*2) + 393), 63)*63) + (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 7))] = @tir.if_then_else((((1 <= floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*2) + 1), 7) + 2), 9) < 8)) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 393), 63)*49)) + (floormod((floordiv( [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv((threadIdx.x_1*2), 7) + 7)*7) + floormod((threadIdx.x_1*2), 7)) + 441)] = @tir.if_then_else((((threadIdx.x_1*2) < 7) && (floormod((threadIdx.x_1*2), 7) < 6)), data[((cse_var_2 + (threadIdx.x_1*2)) + 386)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 4), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 5), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 2), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 7)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2*4), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 7), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 8)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 8), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 3), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 10)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 10), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 11)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 11), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 4), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 13)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 13), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 14)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 14), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 1), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 5), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 16)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 16), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 17)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 17), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 6), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 19)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 19), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 20)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 20), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 7), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 22)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 22), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 23)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 2), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 23), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
}
- if @tir.likely((threadIdx.x_1 < 7), dtype=bool) {
- pad_temp.shared_1[((((floordiv(((threadIdx.x_1*2) + 1), 7) + 7)*7) + floormod(((threadIdx.x_1*2) + 1), 7)) + 441)] = @tir.if_then_else(((((threadIdx.x_1*2) + 1) < 7) && (floormod(((threadIdx.x_1*2) + 1), 7) < 6)), data[((cse_var_2 + ((threadIdx.x_1*2) + 1)) + 386)], 0f32, dtype=float32)
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 24)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 8), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 25)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 25), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 26)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 26), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 27)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 9), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 28)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 28), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 29)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 29), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 30)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floormod((floordiv((threadIdx.x_2*32), 3) + 10), 24)*3)) + floormod((threadIdx.x_2*2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 36), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*32) + 31)] = kernel[(((((blockIdx.x*73728) + (floordiv(((threadIdx.x_2*4) + 3), 9)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((threadIdx.x_2*32) + 31), 72), 3)*3)) + floormod(((threadIdx.x_2*2) + 1), 3))]
}
}
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 1), 24)*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 2), 24)*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 45), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 24)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + 2)]
+ for (rc.outer.inner: int32, 0, 8) {
+ let cse_var_2: int32 = (rc.outer.inner*9)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_2]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 216)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 288)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 360)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 432)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 504)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 147)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 219)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 291)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 363)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 435)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 507)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 150)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 222)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 294)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 366)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 438)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 510)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 576)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 648)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 720)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 792)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 864)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 936)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1008)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[(((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1080)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 579)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 651)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 723)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 795)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 867)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 939)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1011)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1083)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 582)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 654)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 726)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 798)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 870)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 942)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1014)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1086)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 145)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 217)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 289)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 361)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 433)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 505)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 148)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 220)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 292)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 364)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 436)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 508)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 151)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 223)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 295)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 367)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 439)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 511)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 577)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 649)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 721)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 793)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 865)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 937)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1009)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1081)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 580)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 652)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 724)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 796)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 868)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 940)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1012)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1084)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 583)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 655)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 727)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 799)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 871)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 943)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1015)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1087)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 146)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 218)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 290)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 362)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 434)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 506)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 149)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 221)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 293)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 365)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 437)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 509)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 152)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 224)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 296)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 368)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 440)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 512)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 578)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 650)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 722)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 794)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 866)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 938)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1010)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1082)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 581)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 653)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 725)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 797)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 869)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 941)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1013)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1085)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 584)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 656)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 728)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 800)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 872)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 944)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1016)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1088)]))
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[0]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[48]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[72]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[1]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[49]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[73]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[2]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[50]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[74]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[51]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[75]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[4]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[52]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[76]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[5]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[53]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[77]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[54]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[78]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[7]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[55]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[79]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[8]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[56]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[80]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[57]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[81]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[10]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[58]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[82]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[11]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[59]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[83]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[96]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[120]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[144]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[threadIdx.x]*kernel.shared_1[168]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[97]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[121]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[145]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 7)]*kernel.shared_1[169]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[98]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[122]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[146]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 14)]*kernel.shared_1[170]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[123]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[147]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 63)]*kernel.shared_1[171]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[100]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[124]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[148]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 70)]*kernel.shared_1[172]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[101]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[125]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[149]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 77)]*kernel.shared_1[173]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[126]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[150]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 126)]*kernel.shared_1[174]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[103]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[127]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[151]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 133)]*kernel.shared_1[175]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[104]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[128]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[152]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 140)]*kernel.shared_1[176]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[129]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[153]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 189)]*kernel.shared_1[177]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[106]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[130]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[154]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 196)]*kernel.shared_1[178]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[107]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[131]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[155]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 203)]*kernel.shared_1[179]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[60]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[84]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[13]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[61]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[85]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[14]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[62]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[86]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[63]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[87]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[16]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[64]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[88]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[17]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[65]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[89]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[66]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[90]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[19]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[67]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[91]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[20]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[68]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[92]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[69]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[93]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[22]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[70]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[94]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[23]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[71]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[95]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[132]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[156]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 252)]*kernel.shared_1[180]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[109]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[133]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[157]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 259)]*kernel.shared_1[181]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[110]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[134]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[158]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 266)]*kernel.shared_1[182]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[135]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[159]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 315)]*kernel.shared_1[183]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[112]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[136]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[160]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 322)]*kernel.shared_1[184]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[113]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[137]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[161]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 329)]*kernel.shared_1[185]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[138]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[162]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 378)]*kernel.shared_1[186]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[115]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[139]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[163]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 385)]*kernel.shared_1[187]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[116]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[140]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[164]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 392)]*kernel.shared_1[188]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[141]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[165]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 441)]*kernel.shared_1[189]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[118]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[142]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[166]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 448)]*kernel.shared_1[190]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[119]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[143]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[167]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(threadIdx.x + 455)]*kernel.shared_1[191]))
}
}
- for (i1.inner: int32, 0, 8) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 16) {
+ compute[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*16) + i1.inner)]), 0f32)
}
}
}
@@ -1233,7 +827,7 @@ 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: 0.241 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.280 ms
</pre></div>
</div>
</div>
@@ -1262,7 +856,7 @@ 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=4)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=8)
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_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
@@ -1274,17 +868,17 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=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)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=16)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
@@ -1309,16 +903,16 @@ 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=32)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=49)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1337,9 +931,9 @@ CUDA source code:
#define uint64_t unsigned long long
#endif
extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[192];
+ float conv2d_nchw[16];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1348,658 +942,278 @@ extern "C" __global__ void __launch_bounds__(49) default_function_kern
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[15] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = ((((7 <= ((((int)threadIdx.x) * 2) % 63)) && (((((int)threadIdx.x) * 2) % 63) < 56)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 63) * 49)) + ((((int)threadIdx.x) * 2) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = ((((7 <= (((((int)threadIdx.x) * 2) + 1) % 63)) && ((((((int)threadIdx.x) * 2) + 1) % 63) < 56)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 63) * 49)) + (((((int)threadIdx.x) * 2) + 1) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 98) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 98) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 99) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 99) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 196) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 196) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 197) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 197) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 294) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 294) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 295) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 295) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 392) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) < 8)) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 392) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 393) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) < 8)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 393) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) [...]
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 490)] = (((((int)threadIdx.x) < 4) && (1 <= ((((int)threadIdx.x) * 2) % 7))) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 384)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 49)] = (((((9 <= ((((int)threadIdx.x) + 49) % 81)) && (((((int)threadIdx.x) + 49) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 49) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((1 <= ((((int)threadIdx.x) + 8) % 9)) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 147)] = (((((9 <= ((((int)threadIdx.x) + 66) % 81)) && (((((int)threadIdx.x) + 66) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 147) / 81) * 49)) + ((((((int)threadIdx.x) + 66) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 245)] = ((((7 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 245) / 81) * 49)) + (((((int)threadIdx.x) + 2) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 343)] = (((1 <= ((((int)threadIdx.x) + 1) % 9)) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 343) / 81) * 49)) + (((((int)threadIdx.x) + 19) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 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 * 392) + (((((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) + 441)] = (((((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 * 392) + (((((int)threadIdx.x) + 441) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = ((((5 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 490) / 81) * 49)) + (((((int)threadIdx.x) + 4) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 539)] = (((((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 * 392) + (((((int)threadIdx.x) + 539) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + (((((int)threadIdx.x) + 21) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 11) {
+ pad_temp_shared[(((int)threadIdx.x) + 637)] = ((((((int)threadIdx.x) < 2) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 637) / 81) * 49)) + (((((int)threadIdx.x) + 70) / 9) * 7)) + ((int)threadIdx.x)) - 1)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 491)] = (((((int)threadIdx.x) < 3) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 7))) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 385)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[(((int)threadIdx.x) * 32)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 1) % 24) * 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) % 24) * 3))];
- if (((int)threadIdx.x) < 45) {
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 1) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[0]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[48]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[72]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[1]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[49]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[73]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[2]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[50]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[74]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[3]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[51]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[75]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[4]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[52]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[76]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[5]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[53]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[77]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[6]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[54]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[78]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[7]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[55]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[79]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[8]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[56]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[80]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[9]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[57]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[81]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[10]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[58]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[82]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[11]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[59]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[83]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[96]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[120]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[144]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[168]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[97]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[121]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[145]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[169]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[98]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[122]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[146]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[170]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[99]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[123]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[147]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[171]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[100]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[124]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[148]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[172]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[101]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[125]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[149]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[173]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[102]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[126]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[150]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[174]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[103]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[127]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[151]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[175]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[104]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[128]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[152]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[176]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[105]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[129]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[153]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[177]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[106]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[130]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[154]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[178]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[107]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[131]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[155]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[179]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[12]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[60]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[84]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[13]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[61]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[85]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[14]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[62]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[86]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[15]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[63]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[87]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[16]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[64]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[88]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[17]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[65]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[89]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[18]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[66]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[90]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[19]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[67]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[91]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[20]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[68]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[92]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[21]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[69]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[93]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[22]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[70]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[94]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[23]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[71]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[95]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[108]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[132]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[156]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[180]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[109]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[133]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[157]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[181]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[110]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[134]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[158]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[182]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[111]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[135]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[159]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[183]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[112]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[136]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[160]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[184]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[113]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[137]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[161]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[185]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[114]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[138]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[162]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[186]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[115]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[139]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[163]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[187]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[116]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[140]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[164]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[188]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[117]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[141]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[165]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[189]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[118]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[142]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[166]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[190]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[119]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[143]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[167]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[191]));
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = (((7 <= ((((int)threadIdx.x) * 2) % 63)) && (((((int)threadIdx.x) * 2) % 63) < 56)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 63) * 49)) + ((((int)threadIdx.x) * 2) % 63)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((7 <= (((((int)threadIdx.x) * 2) + 1) % 63)) && ((((((int)threadIdx.x) * 2) + 1) % 63) < 56)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 63) * 49)) + (((((int)threadIdx.x) * 2) + 1) % 63)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 98) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 98) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 99) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 99) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0.0 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 196) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 196) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 197) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 197) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 294) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 294) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 295) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 295) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 392) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = (((1 <= ((((((int)threadIdx.x) * 2) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 392) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 393) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = (((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 393) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7)) - 7)] : 0 [...]
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 490)] = ((((int)threadIdx.x) < 4) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 385)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 2) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
}
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 491)] = ((((int)threadIdx.x) < 3) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 386)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 1) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 1)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 1) % 24) * 3)) + 1)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) % 24) * 3)) + 1)];
- if (((int)threadIdx.x) < 45) {
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 4) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[0]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[48]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[72]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[1]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[49]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[73]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[2]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[50]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[74]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[3]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[51]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[75]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[4]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[52]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[76]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[5]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[53]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[77]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[6]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[54]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[78]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[7]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[55]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[79]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[8]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[56]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[80]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[9]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[57]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[81]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[10]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[58]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[82]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[11]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[59]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[83]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[96]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[120]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[144]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[168]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[97]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[121]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[145]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[169]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[98]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[122]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[146]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[170]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[99]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[123]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[147]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[171]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[100]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[124]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[148]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[172]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[101]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[125]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[149]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[173]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[102]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[126]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[150]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[174]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[103]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[127]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[151]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[175]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[104]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[128]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[152]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[176]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[105]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[129]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[153]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[177]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[106]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[130]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[154]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[178]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[107]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[131]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[155]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[179]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[12]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[60]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[84]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[13]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[61]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[85]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[14]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[62]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[86]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[15]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[63]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[87]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[16]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[64]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[88]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[17]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[65]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[89]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[18]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[66]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[90]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[19]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[67]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[91]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[20]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[68]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[92]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[21]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[69]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[93]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[22]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[70]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[94]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[23]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[71]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[95]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[108]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[132]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[156]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[180]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[109]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[133]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[157]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[181]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[110]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[134]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[158]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[182]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[111]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[135]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[159]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[183]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[112]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[136]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[160]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[184]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[113]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[137]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[161]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[185]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[114]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[138]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[162]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[186]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[115]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[139]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[163]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[187]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[116]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[140]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[164]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[188]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[117]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[141]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[165]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[189]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[118]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[142]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[166]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[190]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[119]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[143]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[167]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[191]));
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = ((((7 <= ((((int)threadIdx.x) * 2) % 63)) && (((((int)threadIdx.x) * 2) % 63) < 56)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 2) / 63) * 49)) + ((((int)threadIdx.x) * 2) % 63)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = ((((7 <= (((((int)threadIdx.x) * 2) + 1) % 63)) && ((((((int)threadIdx.x) * 2) + 1) % 63) < 56)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 1) / 63) * 49)) + (((((int)threadIdx.x) * 2) + 1) % 63)) - 6)] : 0.000000e+00f);
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 98) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 98) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 2) [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 99) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 99) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 5) % 9 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 196) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 196) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 2 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 197) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 197) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 1) % [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 294) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 294) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 2 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 295) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 295) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 6) % [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 392) / 63) * 63) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2) % 7))] = ((((1 <= ((((((int)threadIdx.x) * 2) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) < 8)) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 392) / 63) * 49)) + (((((((int)threadIdx.x) * 2) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 2 [...]
- pad_temp_shared[((((((((int)threadIdx.x) * 2) + 393) / 63) * 63) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 7))] = ((((1 <= (((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % 9) < 8)) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 2) + 393) / 63) * 49)) + ((((((((int)threadIdx.x) * 2) + 1) / 7) + 2) % [...]
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 490)] = (((((int)threadIdx.x) < 4) && (((((int)threadIdx.x) * 2) % 7) < 6)) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 386)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 5) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 2) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 7)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) * 4) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 7) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 8)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 8) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 3) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 10)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 10) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 11)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 11) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 4) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
}
- if (((int)threadIdx.x) < 7) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 491)] = (((((int)threadIdx.x) < 3) && ((((((int)threadIdx.x) * 2) + 1) % 7) < 6)) ? data[(((rc_outer_outer * 392) + (((int)threadIdx.x) * 2)) + 387)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 13)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 13) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + 2)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 1) % 24) * 3)) + 2)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 2) % 24) * 3)) + 2)];
- if (((int)threadIdx.x) < 45) {
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 1) & 7) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 14)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 14) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 5) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 16)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 16) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 17)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 17) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 6) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 19)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 19) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 20)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 20) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 7) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 22)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 22) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 23)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 23) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 24)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 8) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 25)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 25) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 26)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 26) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 27)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 9) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 28)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 28) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 29)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 29) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 30)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) / 3) + 10) % 24) * 3)) + ((((int)threadIdx.x) * 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 36) {
+ kernel_shared[((((int)threadIdx.x) * 32) + 31)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 4608)) + (rc_outer_outer * 72)) + (((((((int)threadIdx.x) * 32) + 31) % 72) / 3) * 3)) + (((((int)threadIdx.x) * 2) + 1) % 3))];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[0]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[48]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[72]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[1]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[49]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[73]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[2]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[50]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[74]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[3]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[51]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[75]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[4]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[52]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[76]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[5]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[53]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[77]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[6]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[54]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[78]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[7]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[55]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[79]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[8]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[56]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[80]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[9]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[57]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[81]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[10]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[58]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[82]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[11]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[59]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[83]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[96]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[120]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[144]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((int)threadIdx.x)] * kernel_shared[168]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[97]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[121]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[145]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 7)] * kernel_shared[169]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[98]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[122]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[146]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 14)] * kernel_shared[170]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[99]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[123]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[147]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 63)] * kernel_shared[171]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[100]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[124]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[148]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 70)] * kernel_shared[172]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[101]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[125]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[149]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 77)] * kernel_shared[173]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[102]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[126]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[150]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 126)] * kernel_shared[174]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[103]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[127]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[151]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 133)] * kernel_shared[175]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[104]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[128]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[152]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 140)] * kernel_shared[176]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[105]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[129]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[153]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 189)] * kernel_shared[177]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[106]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[130]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[154]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 196)] * kernel_shared[178]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[107]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[131]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[155]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 203)] * kernel_shared[179]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[12]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[60]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[84]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[13]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[61]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[85]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[14]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[62]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[86]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[15]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[63]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[87]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[16]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[64]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[88]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[17]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[65]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[89]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[18]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[66]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[90]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[19]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[67]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[91]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[20]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[68]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[92]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[21]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[69]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[93]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[22]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[70]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[94]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[23]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[71]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[95]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[108]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[132]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[156]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 252)] * kernel_shared[180]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[109]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[133]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[157]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 259)] * kernel_shared[181]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[110]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[134]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[158]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 266)] * kernel_shared[182]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[111]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[135]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[159]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 315)] * kernel_shared[183]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[112]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[136]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[160]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 322)] * kernel_shared[184]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[113]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[137]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[161]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 329)] * kernel_shared[185]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[114]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[138]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[162]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 378)] * kernel_shared[186]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[115]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[139]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[163]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 385)] * kernel_shared[187]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[116]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[140]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[164]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 392)] * kernel_shared[188]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[117]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[141]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[165]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 441)] * kernel_shared[189]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[118]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[142]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[166]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 448)] * kernel_shared[190]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[119]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[143]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[167]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) + 455)] * kernel_shared[191]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(rc_outer_inner * 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 216)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 288)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 360)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 432)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 504)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 147)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 219)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 291)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 363)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 435)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 507)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 150)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 222)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 294)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 366)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 438)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 510)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 576)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 648)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 720)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 792)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 864)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 936)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 1008)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((rc_outer_inner * 9) + 1080)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 579)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 651)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 723)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 795)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 867)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 939)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 1011)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((rc_outer_inner * 9) + 1083)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 582)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 654)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 726)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 798)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 870)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 942)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 1014)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((rc_outer_inner * 9) + 1086)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 145)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 217)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 289)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 361)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 433)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 505)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 148)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 220)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 292)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 364)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 436)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 508)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 151)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 223)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 295)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 367)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 439)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 511)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 577)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 649)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 721)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 793)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 865)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 937)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 1009)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((rc_outer_inner * 9) + 1081)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 580)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 652)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 724)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 796)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 868)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 940)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 1012)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((rc_outer_inner * 9) + 1084)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 583)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 655)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 727)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 799)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 871)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 943)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 1015)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((rc_outer_inner * 9) + 1087)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 146)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 218)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 290)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 362)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 434)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 506)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 149)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 221)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 293)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 365)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 437)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 509)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 152)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 224)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 296)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 368)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 440)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 512)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 578)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 650)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 722)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 794)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 866)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 938)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 1010)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((rc_outer_inner * 9) + 1082)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 581)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 653)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 725)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 797)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 869)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 941)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 1013)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((rc_outer_inner * 9) + 1085)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 584)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 656)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 728)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 800)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 872)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 944)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 1016)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((rc_outer_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((rc_outer_inner * 9) + 1088)]));
+ }
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -2036,7 +1250,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 16.739 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 18.616 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 b9655f7db..da07f3ea4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.0896 10.0922 10.1559 10.0207 0.0553
+ 10.0024 10.0123 10.0234 9.9716 0.0222
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index cb13e9388..66e6397be 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 758.5364 758.4762 758.7755 758.3574 0.1759
+ 755.5098 755.0214 756.8228 754.6852 0.9385
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.099 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.138 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 0c725296d..7a04fda82 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,121 +620,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), 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_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i.outer.inner*64) + (nb_j.inner*16))
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_2] = 0f32
- compute_5[(cse_var_2 + 1)] = 0f32
- compute_5[(cse_var_2 + 2)] = 0f32
- compute_5[(cse_var_2 + 3)] = 0f32
- compute_5[(cse_var_2 + 4)] = 0f32
- compute_5[(cse_var_2 + 5)] = 0f32
- compute_5[(cse_var_2 + 6)] = 0f32
- compute_5[(cse_var_2 + 7)] = 0f32
- compute_5[(cse_var_2 + 8)] = 0f32
- compute_5[(cse_var_2 + 9)] = 0f32
- compute_5[(cse_var_2 + 10)] = 0f32
- compute_5[(cse_var_2 + 11)] = 0f32
- compute_5[(cse_var_2 + 12)] = 0f32
- compute_5[(cse_var_2 + 13)] = 0f32
- compute_5[(cse_var_2 + 14)] = 0f32
- compute_5[(cse_var_2 + 15)] = 0f32
- compute_5[(cse_var_2 + 32)] = 0f32
- compute_5[(cse_var_2 + 33)] = 0f32
- compute_5[(cse_var_2 + 34)] = 0f32
- compute_5[(cse_var_2 + 35)] = 0f32
- compute_5[(cse_var_2 + 36)] = 0f32
- compute_5[(cse_var_2 + 37)] = 0f32
- compute_5[(cse_var_2 + 38)] = 0f32
- compute_5[(cse_var_2 + 39)] = 0f32
- compute_5[(cse_var_2 + 40)] = 0f32
- compute_5[(cse_var_2 + 41)] = 0f32
- compute_5[(cse_var_2 + 42)] = 0f32
- compute_5[(cse_var_2 + 43)] = 0f32
- compute_5[(cse_var_2 + 44)] = 0f32
- compute_5[(cse_var_2 + 45)] = 0f32
- compute_5[(cse_var_2 + 46)] = 0f32
- compute_5[(cse_var_2 + 47)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- let cse_var_35: int32 = (elem_idx*16)
- let cse_var_34: int32 = (cse_var_2 + 9)
- let cse_var_33: int32 = (cse_var_2 + 8)
- let cse_var_32: int32 = (cse_var_2 + 7)
- let cse_var_31: int32 = (cse_var_2 + 6)
- let cse_var_30: int32 = (cse_var_2 + 5)
- let cse_var_29: int32 = (cse_var_2 + 47)
- let cse_var_28: int32 = (cse_var_2 + 46)
- let cse_var_27: int32 = (cse_var_2 + 45)
- let cse_var_26: int32 = (cse_var_2 + 44)
- let cse_var_25: int32 = (cse_var_2 + 43)
- let cse_var_24: int32 = (cse_var_2 + 42)
- let cse_var_23: int32 = (cse_var_2 + 41)
- let cse_var_22: int32 = (cse_var_2 + 40)
- let cse_var_21: int32 = (cse_var_2 + 4)
- let cse_var_20: int32 = (cse_var_2 + 39)
- let cse_var_19: int32 = (cse_var_2 + 38)
- let cse_var_18: int32 = (cse_var_2 + 37)
- let cse_var_17: int32 = (cse_var_2 + 36)
- let cse_var_16: int32 = (cse_var_2 + 35)
- let cse_var_15: int32 = (cse_var_2 + 34)
- let cse_var_14: int32 = (cse_var_2 + 33)
- let cse_var_13: int32 = (cse_var_2 + 32)
- let cse_var_12: int32 = (cse_var_2 + 3)
- let cse_var_11: int32 = (cse_var_2 + 2)
- let cse_var_10: int32 = (cse_var_2 + 15)
- let cse_var_9: int32 = (cse_var_2 + 14)
- let cse_var_8: int32 = (cse_var_2 + 13)
- let cse_var_7: int32 = (cse_var_2 + 12)
- let cse_var_6: int32 = (cse_var_2 + 11)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*512))
- {
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_35)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- }
- }
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global;
+ for (i1.outer: int32, 0, 64) {
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [64], [])[((i.inner.init*16) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floordiv(i1.outer, 2) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floordiv(i1.outer, 2)
+ let cse_var_2: int32 = ((i.inner*16) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_36: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_36, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_36, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 4) {
+ for (i1.inner: int32, 0, 8) {
+ let cse_var_5: int32 = (i1.outer*8)
+ let cse_var_4: int32 = ((((i0.outer*2048) + (i0.inner*512)) + cse_var_5) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((((i0.inner*16) + cse_var_5) + i1.inner) - (floordiv(i1.outer, 2)*16))] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -772,7 +681,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.468 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.553 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 bc870ed32..6ab66153f 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.801</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.141</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.766</p></td>
+<td><p>00:45.106</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>00:00.020</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 c3c69e5eb..defb3a14e 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1431,8 +1431,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 174.59/174.59 result: MeasureResult(costs=(0.0013259764777777778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0773606300354004, timestamp=1658799774.9398315) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/174.59 result: Traceback (most recent call last):
+No: 9 GFLOPS: 174.65/174.65 result: MeasureResult(costs=(0.0013254985555555556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0453152656555176, timestamp=1658801307.741073) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/174.65 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
@@ -1555,8 +1555,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.67/260.67 result: MeasureResult(costs=(0.0008881046187845305,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7665858268737793, timestamp=1658799775.8549378) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.18/260.18 result: MeasureResult(costs=(0.0008897650828729283,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7439014911651611, timestamp=1658801308.6655772) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.18 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
@@ -1679,7 +1679,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.18 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
@@ -1802,7 +1802,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.18 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
@@ -1925,9 +1925,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.48/260.67 result: MeasureResult(costs=(0.04222365825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8504853248596191, timestamp=1658799780.4401162) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.36/260.67 result: MeasureResult(costs=(0.068928888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.582594633102417, timestamp=1658799781.6768804) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.42/260.18 result: MeasureResult(costs=(0.042678113000000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8313236236572266, timestamp=1658801313.2114427) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/260.18 result: MeasureResult(costs=(0.0693738225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.546748638153076, timestamp=1658801314.4557946) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.18 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1945,8 +1945,8 @@ No: 17 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 26.08/260.67 result: MeasureResult(costs=(0.008878023,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1754045486450195, timestamp=1658799792.5894463) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.80/260.18 result: MeasureResult(costs=(0.008326810928571429,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2733991146087646, timestamp=1658801325.4546382) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.18 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
@@ -2069,7 +2069,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.67 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.18 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
@@ -2232,7 +2232,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001293
+Time cost of this operator: 0.001299
</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 6268b7295..45af8facc 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.735 (1, 2, 10, 10, 3) 2 1 [311.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.024 0.958 (1, 6, 10, 10) 1 1 [3.024]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.308 (1, 1, 10, 10, 3) 1 1 [0.972]
-Total_time - 315.796 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.1 98.718 (1, 2, 10, 10, 3) 2 1 [309.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.046 0.973 (1, 6, 10, 10) 1 1 [3.046]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 0.309 (1, 1, 10, 10, 3) 1 1 [0.967]
+Total_time - 313.113 - - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 151.9 98.219 (1, 6, 10, 10, 1) 2 1 [151.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.799 1.163 (1, 6, 10, 10) 1 1 [1.799]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.618 (1, 1, 10, 10, 3) 1 1 [0.955]
-Total_time - 154.654 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 89.75 97.054 (1, 6, 10, 10, 1) 2 1 [89.75]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.747 1.889 (1, 6, 10, 10) 1 1 [1.747]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.977 1.056 (1, 1, 10, 10, 3) 1 1 [0.977]
+Total_time - 92.474 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 7ef77e06d..d561c52d7 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp7ud5dzzs/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp5m0_tjya/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp7ud5dzzs/images/target contains 8144 images
-/tmp/tmp7ud5dzzs/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp5m0_tjya/images/target contains 8144 images
+/tmp/tmp5m0_tjya/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2132 - accuracy: 0.9247 - val_loss: 0.1246 - val_accuracy: 0.9615
+328/328 - 55s - loss: 0.2034 - accuracy: 0.9298 - val_loss: 0.1293 - val_accuracy: 0.9592
Epoch 2/3
-328/328 - 53s - loss: 0.0995 - accuracy: 0.9636 - val_loss: 0.1065 - val_accuracy: 0.9641
+328/328 - 53s - loss: 0.0969 - accuracy: 0.9645 - val_loss: 0.1170 - val_accuracy: 0.9603
Epoch 3/3
-328/328 - 52s - loss: 0.0642 - accuracy: 0.9764 - val_loss: 0.1033 - val_accuracy: 0.9675
+328/328 - 52s - loss: 0.0691 - accuracy: 0.9748 - val_loss: 0.0996 - val_accuracy: 0.9668
-<keras.callbacks.History object at 0x7fa987b33750>
+<keras.callbacks.History object at 0x7fe791228f90>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 2.838 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 4.082 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 f3411e66f..ab8547dd6 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:52.077</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:50.911</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:02.838</p></td>
+<td><p>05:04.082</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:45.473</p></td>
+<td><p>00:43.505</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>00:03.764</p></td>
+<td><p>00:03.322</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index c5be82383..3016efa13 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.592</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:41.590</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.847</p></td>
+<td><p>00:30.343</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.059</p></td>
+<td><p>00:09.729</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>00:01.679</p></td>
+<td><p>00:01.511</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 191b07d82..d4d7a45e4 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -517,7 +517,7 @@ 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 0x7fa9033e9e60>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fe710e66710>
</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 96783f560..1cbf69df2 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.235</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.008</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.932</p></td>
+<td><p>00:01.870</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>00:01.035</p></td>
+<td><p>00:00.907</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>00:00.541</p></td>
+<td><p>00:00.538</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>00:00.525</p></td>
+<td><p>00:00.509</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>00:00.102</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.044</p></td>
+<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>00:00.040</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><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>00:00.041</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 3a7f22371..91a7a9e9b 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -572,7 +572,7 @@ 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/tmpg15hcu9o/input0.cc'\nsource_filename = \"/tmp/tmpg15hcu9o/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/tmpjjc__28l/input0.cc'\nsource_filename = \"/tmp/tmpjjc__28l/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 5cc9e81dc..e14ec57fb 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1597,7 +1597,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1881,7 +1881,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 52939a9be..62fdfa55e 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/ca2ec5429/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 d9d22165e..f498d60f4 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/ca2ec5429/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 ee3a33350..e57eeb2c9 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/ca2ec5429/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 192a6e2eb..c5721f0e2 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/ca2ec5429/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 99ca9ff3c..003956f6a 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/ca2ec5429/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 7d5250d6b..120abba13 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/ca2ec5429/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 e2a35387c..b116935c9 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/ca2ec5429/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 ed046239c..e58d35a40 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/ca2ec5429/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ca2ec5429/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 4f4f54cf1..8b97e3689 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/ca2ec5429/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 c262f14fa..53fe743b9 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/ca2ec5429/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 46b8a6114..5f1c328d0 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/ca2ec5429/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 8d010b7d6..fa50fce12 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/ca2ec5429/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 24d42580e..80f0ff654 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/ca2ec5429/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 97e221b07..bb5cde86d 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/ca2ec5429/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 40d5a9a2f..198f5d758 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/ca2ec5429/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 b2a73ad13..954a6adf9 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/ca2ec5429/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 15966fca9..940bc33c7 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/ca2ec5429/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 eb0bb57d7..f053891a1 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/ca2ec5429/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 b3f6e9e3e..6209761a7 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/ca2ec5429/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 ab702193e..e798aab3d 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/ca2ec5429/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 7c6c1f4b6..91cf362af 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/ca2ec5429/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ca2ec5429/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 848e03cf1..cdace6008 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/ca2ec5429/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 9b3b0d476..b462626b4 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/ca2ec5429/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 df7ecb0fb..25cd31b6b 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/ca2ec5429/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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/ca2ec5429/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9963b59ff/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 9d867490f..8f7f1ecc4 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 a6b86d3da..b4013907d 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:21.680</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.388</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -331,7 +331,7 @@
</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>00:21.673</p></td>
+<td><p>00:21.382</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 b66d2311c..086f4048b 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 23.51s!
+resnet18_v1 inference graph built in 22.71s!
</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 afb4f515f..7fcfd8966 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.31s!
+yolov3-tiny inference graph built in 16.16s!
</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 b9909d0a6..580bc6c14 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:33.000</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.929</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.126</p></td>
+<td><p>00:48.962</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:43.875</p></td>
+<td><p>00:42.968</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 aa8b1c664..d93b5ebfa 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.332</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.192</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.926</p></td>
+<td><p>00:02.801</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>00:00.406</p></td>
+<td><p>00:00.391</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 68f2e3d75..cefd29b1f 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.748</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.689</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.405</p></td>
+<td><p>00:00.367</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>00:00.343</p></td>
+<td><p>00:00.321</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 fc843c2ec..d5363d8a7 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -561,7 +561,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.910 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.744 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index a4b03b884..4555d944b 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -663,16 +663,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 9.27/9.27 result: MeasureResult(costs=(0.0289464058,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5999782085418701, timestamp=1658798571.0366173) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.61/9.27 result: MeasureResult(costs=(0.10298805660000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.793806791305542, timestamp=1658798572.8589933) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0228047482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5762436389923096, timestamp=1658798573.9334927) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.72/11.77 result: MeasureResult(costs=(0.1561022328,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621882438659668, timestamp=1658798577.130506) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.61/11.77 result: MeasureResult(costs=(0.07442361620000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3280863761901855, timestamp=1658798578.5874043) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.81/11.77 result: MeasureResult(costs=(0.1485806234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.540088176727295, timestamp=1658798581.171624) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.77 result: MeasureResult(costs=(0.30786764180000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.047713756561279, timestamp=1658798586.7968082) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.50/11.77 result: MeasureResult(costs=(0.025567515800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5525057315826416, timestamp=1658798587.3709717) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.89/11.77 result: MeasureResult(costs=(0.14188633820000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3703463077545166, timestamp=1658798589.8611484) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.50/11.77 result: MeasureResult(costs=(0.1072656572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8356046676635742, timestamp=1658798591.7556534) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.33/10.33 result: MeasureResult(costs=(0.025990367400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5508499145507812, timestamp=1658800125.9183948) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.94/10.33 result: MeasureResult(costs=(0.0912114386,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.611830472946167, timestamp=1658800128.0720844) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.82/11.82 result: MeasureResult(costs=(0.0227165708,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5627841949462891, timestamp=1658800129.1300826) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.88/11.82 result: MeasureResult(costs=(0.1431279612,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.407961130142212, timestamp=1658800131.5828235) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.67/11.82 result: MeasureResult(costs=(0.0732059746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3079211711883545, timestamp=1658800133.0200145) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.76/11.82 result: MeasureResult(costs=(0.152624874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.603809118270874, timestamp=1658800135.6682804) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.82 result: MeasureResult(costs=(0.3074617414,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.038850784301758, timestamp=1658800141.277615) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.76/11.82 result: MeasureResult(costs=(0.0249518638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5428321361541748, timestamp=1658800141.8420198) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.92/11.82 result: MeasureResult(costs=(0.13997261,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3405919075012207, timestamp=1658800144.302424) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.79/11.82 result: MeasureResult(costs=(0.0963210524,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6469123363494873, timestamp=1658800146.0075746) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 2e6c9c72d..136e17693 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -545,7 +545,7 @@ 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': 497.23278908998964, 'median': 497.44790824997835, 'std': 0.4699869257931475}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 495.31586558001436, 'median': 495.21892269999626, 'std': 0.4674847601802359}
</pre></div>
</div>
</div>
@@ -700,179 +700,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 6.42 s
-[Task 1/25] Current/Best: 6.07/ 17.42 GFLOPS | Progress: (8/20) | 9.43 s
-[Task 1/25] Current/Best: 11.53/ 22.72 GFLOPS | Progress: (12/20) | 11.91 s
-[Task 1/25] Current/Best: 16.67/ 22.79 GFLOPS | Progress: (16/20) | 13.61 s
-[Task 1/25] Current/Best: 11.60/ 23.92 GFLOPS | Progress: (20/20) | 15.36 s Done.
+[Task 1/25] Current/Best: 17.30/ 17.30 GFLOPS | Progress: (4/20) | 6.27 s
+[Task 1/25] Current/Best: 6.14/ 17.30 GFLOPS | Progress: (8/20) | 9.28 s
+[Task 1/25] Current/Best: 11.53/ 22.61 GFLOPS | Progress: (12/20) | 11.77 s
+[Task 1/25] Current/Best: 16.80/ 22.73 GFLOPS | Progress: (16/20) | 13.46 s
+[Task 1/25] Current/Best: 11.56/ 23.90 GFLOPS | Progress: (20/20) | 15.20 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.20/ 13.04 GFLOPS | Progress: (4/20) | 3.80 s
-[Task 2/25] Current/Best: 14.10/ 18.52 GFLOPS | Progress: (8/20) | 5.10 s
-[Task 2/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (12/20) | 6.43 s
-[Task 2/25] Current/Best: 12.28/ 20.97 GFLOPS | Progress: (16/20) | 7.69 s
-[Task 2/25] Current/Best: 19.70/ 20.97 GFLOPS | Progress: (20/20) | 9.33 s Done.
+[Task 2/25] Current/Best: 12.26/ 12.96 GFLOPS | Progress: (4/20) | 3.91 s
+[Task 2/25] Current/Best: 14.18/ 18.66 GFLOPS | Progress: (8/20) | 5.19 s
+[Task 2/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (12/20) | 6.51 s
+[Task 2/25] Current/Best: 11.76/ 21.13 GFLOPS | Progress: (16/20) | 7.77 s
+[Task 2/25] Current/Best: 19.35/ 21.13 GFLOPS | Progress: (20/20) | 9.41 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 10.57 GFLOPS | Progress: (4/20) | 5.89 s
-[Task 3/25] Current/Best: 15.52/ 16.89 GFLOPS | Progress: (8/20) | 7.81 s
-[Task 3/25] Current/Best: 14.88/ 16.89 GFLOPS | Progress: (12/20) | 9.54 s
-[Task 3/25] Current/Best: 7.20/ 23.74 GFLOPS | Progress: (16/20) | 11.46 s
-[Task 3/25] Current/Best: 11.05/ 23.74 GFLOPS | Progress: (20/20) | 16.10 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.58 GFLOPS | Progress: (4/20) | 5.87 s
+[Task 3/25] Current/Best: 15.57/ 16.88 GFLOPS | Progress: (8/20) | 7.78 s
+[Task 3/25] Current/Best: 14.89/ 16.88 GFLOPS | Progress: (12/20) | 9.50 s
+[Task 3/25] Current/Best: 7.21/ 23.76 GFLOPS | Progress: (16/20) | 11.41 s
+[Task 3/25] Current/Best: 12.57/ 23.76 GFLOPS | Progress: (20/20) | 16.00 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.58/ 20.41 GFLOPS | Progress: (4/20) | 2.42 s
-[Task 4/25] Current/Best: 6.51/ 20.41 GFLOPS | Progress: (8/20) | 7.22 s
-[Task 4/25] Current/Best: 22.24/ 22.24 GFLOPS | Progress: (12/20) | 12.15 s
-[Task 4/25] Current/Best: 16.68/ 22.24 GFLOPS | Progress: (16/20) | 14.59 s
-[Task 4/25] Current/Best: 13.28/ 22.24 GFLOPS | Progress: (20/20) | 16.58 s Done.
+[Task 4/25] Current/Best: 9.55/ 20.31 GFLOPS | Progress: (4/20) | 2.40 s
+[Task 4/25] Current/Best: 6.87/ 20.31 GFLOPS | Progress: (8/20) | 7.16 s
+[Task 4/25] Current/Best: 21.76/ 21.76 GFLOPS | Progress: (12/20) | 12.21 s
+[Task 4/25] Current/Best: 16.82/ 21.76 GFLOPS | Progress: (16/20) | 14.64 s
+[Task 4/25] Current/Best: 13.09/ 21.76 GFLOPS | Progress: (20/20) | 16.70 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.46/ 10.22 GFLOPS | Progress: (4/20) | 2.62 s
-[Task 5/25] Current/Best: 11.70/ 12.57 GFLOPS | Progress: (8/20) | 4.68 s
-[Task 5/25] Current/Best: 11.19/ 17.97 GFLOPS | Progress: (12/20) | 7.93 s
-[Task 5/25] Current/Best: 11.69/ 22.95 GFLOPS | Progress: (16/20) | 9.38 s
-[Task 5/25] Current/Best: 11.71/ 22.95 GFLOPS | Progress: (20/20) | 11.29 s Done.
+[Task 5/25] Current/Best: 9.71/ 10.39 GFLOPS | Progress: (4/20) | 2.59 s
+[Task 5/25] Current/Best: 11.85/ 12.72 GFLOPS | Progress: (8/20) | 4.65 s
+[Task 5/25] Current/Best: 11.44/ 18.02 GFLOPS | Progress: (12/20) | 7.72 s
+[Task 5/25] Current/Best: 11.80/ 22.58 GFLOPS | Progress: (16/20) | 9.13 s
+[Task 5/25] Current/Best: 12.13/ 22.58 GFLOPS | Progress: (20/20) | 11.03 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.19/ 20.68 GFLOPS | Progress: (4/20) | 4.19 s
-[Task 6/25] Current/Best: 18.96/ 20.68 GFLOPS | Progress: (8/20) | 5.96 s
-[Task 6/25] Current/Best: 13.25/ 20.68 GFLOPS | Progress: (12/20) | 7.93 s
-[Task 6/25] Current/Best: 19.97/ 20.68 GFLOPS | Progress: (16/20) | 10.21 s
-[Task 6/25] Current/Best: 3.71/ 20.68 GFLOPS | Progress: (20/20) | 12.77 s Done.
+[Task 6/25] Current/Best: 12.19/ 20.71 GFLOPS | Progress: (4/20) | 4.13 s
+[Task 6/25] Current/Best: 18.95/ 20.71 GFLOPS | Progress: (8/20) | 5.88 s
+[Task 6/25] Current/Best: 13.25/ 20.71 GFLOPS | Progress: (12/20) | 7.83 s
+[Task 6/25] Current/Best: 19.96/ 20.71 GFLOPS | Progress: (16/20) | 10.08 s
+[Task 6/25] Current/Best: 3.74/ 20.71 GFLOPS | Progress: (20/20) | 12.61 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.23/ 12.93 GFLOPS | Progress: (4/20) | 3.58 s
-[Task 7/25] Current/Best: 20.21/ 20.94 GFLOPS | Progress: (8/20) | 5.09 s
-[Task 7/25] Current/Best: 15.63/ 20.94 GFLOPS | Progress: (12/20) | 7.01 s
-[Task 7/25] Current/Best: 12.21/ 20.94 GFLOPS | Progress: (16/20) | 9.07 s
-[Task 7/25] Current/Best: 6.28/ 21.62 GFLOPS | Progress: (20/20) | 11.55 s Done.
+[Task 7/25] Current/Best: 11.23/ 12.20 GFLOPS | Progress: (4/20) | 3.65 s
+[Task 7/25] Current/Best: 20.31/ 21.15 GFLOPS | Progress: (8/20) | 5.18 s
+[Task 7/25] Current/Best: 16.20/ 21.15 GFLOPS | Progress: (12/20) | 7.10 s
+[Task 7/25] Current/Best: 12.24/ 21.15 GFLOPS | Progress: (16/20) | 9.15 s
+[Task 7/25] Current/Best: 6.36/ 21.71 GFLOPS | Progress: (20/20) | 11.63 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.26/ 14.12 GFLOPS | Progress: (4/20) | 2.92 s
-[Task 8/25] Current/Best: 9.53/ 14.12 GFLOPS | Progress: (8/20) | 8.13 s
-[Task 8/25] Current/Best: 13.01/ 14.12 GFLOPS | Progress: (12/20) | 14.76 s
-[Task 8/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (16/20) | 16.89 s
-[Task 8/25] Current/Best: 19.67/ 19.67 GFLOPS | Progress: (20/20) | 24.08 s Done.
+[Task 8/25] Current/Best: 10.11/ 14.08 GFLOPS | Progress: (4/20) | 2.92 s
+[Task 8/25] Current/Best: 9.84/ 14.08 GFLOPS | Progress: (8/20) | 8.03 s
+[Task 8/25] Current/Best: 12.57/ 14.08 GFLOPS | Progress: (12/20) | 14.56 s
+[Task 8/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (16/20) | 16.67 s
+[Task 8/25] Current/Best: 20.20/ 20.20 GFLOPS | Progress: (20/20) | 23.83 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.34/ 15.58 GFLOPS | Progress: (4/20) | 11.97 s
-[Task 9/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 13.73 s
-[Task 9/25] Current/Best: 8.24/ 23.46 GFLOPS | Progress: (12/20) | 16.27 s
-[Task 9/25] Current/Best: 17.99/ 23.46 GFLOPS | Progress: (16/20) | 19.19 s
-[Task 9/25] Current/Best: 9.17/ 23.46 GFLOPS | Progress: (20/20) | 28.00 s
+[Task 9/25] Current/Best: 14.20/ 15.85 GFLOPS | Progress: (4/20) | 11.97 s
+[Task 9/25] Current/Best: 23.40/ 23.40 GFLOPS | Progress: (8/20) | 13.71 s
+[Task 9/25] Current/Best: 8.19/ 23.40 GFLOPS | Progress: (12/20) | 16.24 s
+[Task 9/25] Current/Best: 17.98/ 23.40 GFLOPS | Progress: (16/20) | 19.03 s
+[Task 9/25] Current/Best: 9.22/ 23.40 GFLOPS | Progress: (20/20) | 27.72 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (4/20) | 2.58 s
-[Task 10/25] Current/Best: 15.40/ 18.21 GFLOPS | Progress: (8/20) | 4.23 s
-[Task 10/25] Current/Best: 12.49/ 18.70 GFLOPS | Progress: (12/20) | 5.78 s
-[Task 10/25] Current/Best: 19.18/ 20.20 GFLOPS | Progress: (16/20) | 6.90 s
-[Task 10/25] Current/Best: 8.89/ 20.20 GFLOPS | Progress: (20/20) | 8.45 s Done.
+[Task 10/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (4/20) | 2.58 s
+[Task 10/25] Current/Best: 15.52/ 18.26 GFLOPS | Progress: (8/20) | 4.21 s
+[Task 10/25] Current/Best: 12.80/ 18.91 GFLOPS | Progress: (12/20) | 5.76 s
+[Task 10/25] Current/Best: 19.18/ 20.31 GFLOPS | Progress: (16/20) | 6.86 s
+[Task 10/25] Current/Best: 8.93/ 20.31 GFLOPS | Progress: (20/20) | 8.38 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.29/ 18.10 GFLOPS | Progress: (4/20) | 3.39 s
-[Task 11/25] Current/Best: 16.98/ 18.10 GFLOPS | Progress: (8/20) | 6.21 s
-[Task 11/25] Current/Best: 18.05/ 18.10 GFLOPS | Progress: (12/20) | 8.26 s
-[Task 11/25] Current/Best: 13.48/ 21.10 GFLOPS | Progress: (16/20) | 11.18 s
-[Task 11/25] Current/Best: 19.43/ 21.47 GFLOPS | Progress: (20/20) | 13.27 s Done.
+[Task 11/25] Current/Best: 12.28/ 18.07 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 11/25] Current/Best: 16.89/ 18.07 GFLOPS | Progress: (8/20) | 6.15 s
+[Task 11/25] Current/Best: 18.10/ 18.10 GFLOPS | Progress: (12/20) | 8.20 s
+[Task 11/25] Current/Best: 12.12/ 21.23 GFLOPS | Progress: (16/20) | 11.17 s
+[Task 11/25] Current/Best: 19.45/ 21.23 GFLOPS | Progress: (20/20) | 13.30 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.78/ 18.02 GFLOPS | Progress: (4/20) | 5.75 s
-[Task 12/25] Current/Best: 5.21/ 18.02 GFLOPS | Progress: (8/20) | 9.75 s
-[Task 12/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (12/20) | 11.79 s
-[Task 12/25] Current/Best: 15.22/ 18.79 GFLOPS | Progress: (16/20) | 14.78 s
-[Task 12/25] Current/Best: 15.09/ 18.79 GFLOPS | Progress: (20/20) | 16.71 s Done.
+[Task 12/25] Current/Best: 7.77/ 18.06 GFLOPS | Progress: (4/20) | 5.82 s
+[Task 12/25] Current/Best: 5.29/ 18.06 GFLOPS | Progress: (8/20) | 9.78 s
+[Task 12/25] Current/Best: 18.34/ 18.87 GFLOPS | Progress: (12/20) | 11.76 s
+[Task 12/25] Current/Best: 15.11/ 18.87 GFLOPS | Progress: (16/20) | 14.70 s
+[Task 12/25] Current/Best: 15.08/ 18.99 GFLOPS | Progress: (20/20) | 16.67 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.73/ 17.29 GFLOPS | Progress: (4/20) | 3.80 s
-[Task 13/25] Current/Best: 15.88/ 20.82 GFLOPS | Progress: (8/20) | 6.45 s
-[Task 13/25] Current/Best: 19.44/ 21.61 GFLOPS | Progress: (12/20) | 9.47 s
-[Task 13/25] Current/Best: 12.23/ 21.61 GFLOPS | Progress: (16/20) | 12.90 s
-[Task 13/25] Current/Best: 18.66/ 21.61 GFLOPS | Progress: (20/20) | 15.24 s Done.
+[Task 13/25] Current/Best: 8.68/ 17.27 GFLOPS | Progress: (4/20) | 3.76 s
+[Task 13/25] Current/Best: 15.45/ 20.73 GFLOPS | Progress: (8/20) | 6.41 s
+[Task 13/25] Current/Best: 19.32/ 21.47 GFLOPS | Progress: (12/20) | 9.46 s
+[Task 13/25] Current/Best: 12.19/ 21.47 GFLOPS | Progress: (16/20) | 12.93 s
+[Task 13/25] Current/Best: 18.40/ 21.47 GFLOPS | Progress: (20/20) | 15.30 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.59/ 13.59 GFLOPS | Progress: (4/20) | 3.45 s
-[Task 14/25] Current/Best: 6.06/ 13.59 GFLOPS | Progress: (8/20) | 5.66 s
-[Task 14/25] Current/Best: 20.10/ 20.10 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 14/25] Current/Best: 15.97/ 20.10 GFLOPS | Progress: (16/20) | 9.99 s Done.
+[Task 14/25] Current/Best: 13.59/ 13.59 GFLOPS | Progress: (4/20) | 3.41 s
+[Task 14/25] Current/Best: 6.07/ 13.59 GFLOPS | Progress: (8/20) | 5.58 s
+[Task 14/25] Current/Best: 19.23/ 19.23 GFLOPS | Progress: (12/20) | 8.27 s
+[Task 14/25] Current/Best: 17.07/ 19.23 GFLOPS | Progress: (16/20) | 9.96 s Done.
-[Task 14/25] Current/Best: 17.28/ 20.10 GFLOPS | Progress: (20/20) | 11.82 s
+[Task 14/25] Current/Best: 17.33/ 19.23 GFLOPS | Progress: (20/20) | 11.71 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.14/ 17.62 GFLOPS | Progress: (4/20) | 2.75 s
-[Task 15/25] Current/Best: 14.32/ 17.98 GFLOPS | Progress: (8/20) | 4.09 s
-[Task 15/25] Current/Best: 10.40/ 22.27 GFLOPS | Progress: (12/20) | 6.41 s
-[Task 15/25] Current/Best: 20.38/ 22.27 GFLOPS | Progress: (16/20) | 9.89 s
-[Task 15/25] Current/Best: 9.68/ 22.27 GFLOPS | Progress: (20/20) | 10.91 s
+[Task 15/25] Current/Best: 16.13/ 17.63 GFLOPS | Progress: (4/20) | 2.74 s
+[Task 15/25] Current/Best: 14.37/ 18.07 GFLOPS | Progress: (8/20) | 4.08 s
+[Task 15/25] Current/Best: 10.38/ 22.31 GFLOPS | Progress: (12/20) | 6.33 s
+[Task 15/25] Current/Best: 20.42/ 22.31 GFLOPS | Progress: (16/20) | 9.99 s
+[Task 15/25] Current/Best: 9.70/ 22.31 GFLOPS | Progress: (20/20) | 11.00 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (4/20) | 3.02 s
-[Task 16/25] Current/Best: 3.04/ 20.58 GFLOPS | Progress: (8/20) | 4.69 s
-[Task 16/25] Current/Best: 19.38/ 20.58 GFLOPS | Progress: (12/20) | 5.92 s
-[Task 16/25] Current/Best: 17.17/ 20.58 GFLOPS | Progress: (16/20) | 7.30 s
-[Task 16/25] Current/Best: 9.97/ 21.13 GFLOPS | Progress: (20/20) | 9.49 s Done.
+[Task 16/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (4/20) | 2.91 s
+[Task 16/25] Current/Best: 3.00/ 20.64 GFLOPS | Progress: (8/20) | 4.52 s
+[Task 16/25] Current/Best: 19.64/ 20.64 GFLOPS | Progress: (12/20) | 5.74 s
+[Task 16/25] Current/Best: 18.06/ 20.64 GFLOPS | Progress: (16/20) | 7.13 s
+[Task 16/25] Current/Best: 10.02/ 22.09 GFLOPS | Progress: (20/20) | 9.28 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.35/ 18.50 GFLOPS | Progress: (4/20) | 4.86 s
-[Task 17/25] Current/Best: 13.17/ 23.21 GFLOPS | Progress: (8/20) | 7.80 s
-[Task 17/25] Current/Best: 16.75/ 23.21 GFLOPS | Progress: (12/20) | 9.87 s
-[Task 17/25] Current/Best: 16.42/ 23.21 GFLOPS | Progress: (16/20) | 12.10 s
-[Task 17/25] Current/Best: 10.01/ 23.21 GFLOPS | Progress: (20/20) | 14.28 s Done.
+[Task 17/25] Current/Best: 12.93/ 18.88 GFLOPS | Progress: (4/20) | 4.82 s
+[Task 17/25] Current/Best: 14.17/ 23.34 GFLOPS | Progress: (8/20) | 7.73 s
+[Task 17/25] Current/Best: 16.85/ 23.34 GFLOPS | Progress: (12/20) | 9.78 s
+[Task 17/25] Current/Best: 16.47/ 23.34 GFLOPS | Progress: (16/20) | 12.02 s
+[Task 17/25] Current/Best: 10.04/ 23.34 GFLOPS | Progress: (20/20) | 14.18 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.37/ 17.23 GFLOPS | Progress: (4/20) | 3.86 s
-[Task 18/25] Current/Best: 10.56/ 20.09 GFLOPS | Progress: (8/20) | 7.61 s
-[Task 18/25] Current/Best: 18.74/ 20.09 GFLOPS | Progress: (12/20) | 9.53 s
-[Task 18/25] Current/Best: 9.96/ 20.09 GFLOPS | Progress: (16/20) | 13.48 s
-[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.98 s Done.
+[Task 18/25] Current/Best: 11.37/ 18.02 GFLOPS | Progress: (4/20) | 3.80 s
+[Task 18/25] Current/Best: 10.60/ 19.91 GFLOPS | Progress: (8/20) | 7.53 s
+[Task 18/25] Current/Best: 18.79/ 19.91 GFLOPS | Progress: (12/20) | 9.48 s
+[Task 18/25] Current/Best: 10.03/ 19.91 GFLOPS | Progress: (16/20) | 13.33 s
+[Task 18/25] Current/Best: 20.93/ 20.93 GFLOPS | Progress: (20/20) | 14.85 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 6.92/ 20.25 GFLOPS | Progress: (4/20) | 6.24 s
-[Task 19/25] Current/Best: 2.60/ 20.25 GFLOPS | Progress: (8/20) | 9.60 s
-[Task 19/25] Current/Best: 19.80/ 21.21 GFLOPS | Progress: (12/20) | 12.61 s
-[Task 19/25] Current/Best: 15.02/ 21.36 GFLOPS | Progress: (16/20) | 15.66 s
-[Task 19/25] Current/Best: 2.70/ 23.19 GFLOPS | Progress: (20/20) | 18.48 s Done.
+[Task 19/25] Current/Best: 7.22/ 20.35 GFLOPS | Progress: (4/20) | 6.11 s
+[Task 19/25] Current/Best: 2.59/ 20.35 GFLOPS | Progress: (8/20) | 9.42 s
+[Task 19/25] Current/Best: 20.03/ 21.01 GFLOPS | Progress: (12/20) | 12.37 s
+[Task 19/25] Current/Best: 13.53/ 21.01 GFLOPS | Progress: (16/20) | 15.43 s
+[Task 19/25] Current/Best: 2.70/ 23.43 GFLOPS | Progress: (20/20) | 18.24 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.29/ 14.87 GFLOPS | Progress: (4/20) | 3.39 s Done.
+[Task 20/25] Current/Best: 9.70/ 15.43 GFLOPS | Progress: (4/20) | 3.29 s Done.
Done.
-[Task 20/25] Current/Best: 10.15/ 14.87 GFLOPS | Progress: (8/20) | 6.97 s
-[Task 20/25] Current/Best: 2.32/ 16.57 GFLOPS | Progress: (12/20) | 10.96 s
-[Task 20/25] Current/Best: 12.52/ 16.57 GFLOPS | Progress: (16/20) | 14.92 s
-[Task 20/25] Current/Best: 13.14/ 21.48 GFLOPS | Progress: (20/20) | 17.06 s
+[Task 20/25] Current/Best: 10.60/ 15.43 GFLOPS | Progress: (8/20) | 6.81 s
+[Task 20/25] Current/Best: 2.33/ 16.67 GFLOPS | Progress: (12/20) | 10.99 s
+[Task 20/25] Current/Best: 12.43/ 16.67 GFLOPS | Progress: (16/20) | 14.94 s
+[Task 20/25] Current/Best: 13.49/ 22.12 GFLOPS | Progress: (20/20) | 17.04 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.53 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 21/25] Current/Best: 14.46/ 17.53 GFLOPS | Progress: (8/20) | 4.97 s
-[Task 21/25] Current/Best: 1.61/ 17.53 GFLOPS | Progress: (12/20) | 7.15 s
-[Task 21/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (16/20) | 10.71 s
-[Task 21/25] Current/Best: 4.46/ 18.09 GFLOPS | Progress: (20/20) | 18.14 s
+[Task 21/25] Current/Best: 6.40/ 17.69 GFLOPS | Progress: (4/20) | 3.28 s
+[Task 21/25] Current/Best: 14.61/ 17.69 GFLOPS | Progress: (8/20) | 4.82 s
+[Task 21/25] Current/Best: 1.61/ 17.69 GFLOPS | Progress: (12/20) | 6.93 s
+[Task 21/25] Current/Best: 16.28/ 17.69 GFLOPS | Progress: (16/20) | 10.47 s
+[Task 21/25] Current/Best: 4.45/ 17.69 GFLOPS | Progress: (20/20) | 17.86 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 17.01 GFLOPS | Progress: (4/20) | 2.72 s
-[Task 22/25] Current/Best: 9.06/ 21.88 GFLOPS | Progress: (8/20) | 4.77 s
-[Task 22/25] Current/Best: 19.94/ 21.88 GFLOPS | Progress: (12/20) | 7.16 s
-[Task 22/25] Current/Best: 15.34/ 21.88 GFLOPS | Progress: (16/20) | 9.32 s
-[Task 22/25] Current/Best: 14.61/ 21.88 GFLOPS | Progress: (20/20) | 11.07 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.03 GFLOPS | Progress: (4/20) | 2.69 s
+[Task 22/25] Current/Best: 8.83/ 21.59 GFLOPS | Progress: (8/20) | 4.74 s
+[Task 22/25] Current/Best: 19.86/ 21.59 GFLOPS | Progress: (12/20) | 7.12 s
+[Task 22/25] Current/Best: 15.13/ 21.59 GFLOPS | Progress: (16/20) | 9.26 s
+[Task 22/25] Current/Best: 14.29/ 21.59 GFLOPS | Progress: (20/20) | 11.01 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.32/ 20.34 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 23/25] Current/Best: 15.78/ 20.34 GFLOPS | Progress: (8/20) | 6.72 s
-[Task 23/25] Current/Best: 20.74/ 21.43 GFLOPS | Progress: (12/20) | 8.59 s
-[Task 23/25] Current/Best: 6.32/ 21.43 GFLOPS | Progress: (16/20) | 15.81 s
-[Task 23/25] Current/Best: 7.58/ 21.43 GFLOPS | Progress: (20/20) | 20.08 s Done.
+[Task 23/25] Current/Best: 17.09/ 20.46 GFLOPS | Progress: (4/20) | 3.27 s
+[Task 23/25] Current/Best: 15.92/ 20.46 GFLOPS | Progress: (8/20) | 6.64 s
+[Task 23/25] Current/Best: 20.82/ 21.52 GFLOPS | Progress: (12/20) | 8.50 s
+[Task 23/25] Current/Best: 6.39/ 21.52 GFLOPS | Progress: (16/20) | 15.67 s
+[Task 23/25] Current/Best: 7.65/ 21.52 GFLOPS | Progress: (20/20) | 19.92 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.67/ 8.67 GFLOPS | Progress: (4/20) | 11.84 s
-[Task 24/25] Current/Best: 3.32/ 8.67 GFLOPS | Progress: (8/20) | 23.11 s
-[Task 24/25] Current/Best: 4.25/ 8.67 GFLOPS | Progress: (12/20) | 33.84 s Done.
- Done.
+[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.84 s
+[Task 24/25] Current/Best: 2.13/ 8.58 GFLOPS | Progress: (8/20) | 22.89 s
+[Task 24/25] Current/Best: 4.43/ 8.58 GFLOPS | Progress: (12/20) | 34.45 s Done.
-[Task 24/25] Current/Best: 6.75/ 8.67 GFLOPS | Progress: (16/20) | 39.68 s
-[Task 24/25] Current/Best: 3.21/ 8.79 GFLOPS | Progress: (20/20) | 45.85 s Done.
+[Task 24/25] Current/Best: 6.97/ 8.67 GFLOPS | Progress: (16/20) | 40.23 s
+[Task 24/25] Current/Best: 3.26/ 8.75 GFLOPS | Progress: (20/20) | 46.22 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.85 GFLOPS | Progress: (4/20) | 11.60 s
-[Task 25/25] Current/Best: 5.65/ 7.55 GFLOPS | Progress: (8/20) | 22.88 s
-[Task 25/25] Current/Best: 5.84/ 7.55 GFLOPS | Progress: (12/20) | 34.37 s
-[Task 25/25] Current/Best: 5.65/ 8.79 GFLOPS | Progress: (16/20) | 36.16 s
-[Task 25/25] Current/Best: 2.89/ 8.79 GFLOPS | Progress: (20/20) | 46.84 s
+[Task 25/25] Current/Best: 1.55/ 2.92 GFLOPS | Progress: (4/20) | 11.61 s
+[Task 25/25] Current/Best: 5.61/ 7.84 GFLOPS | Progress: (8/20) | 22.90 s
+[Task 25/25] Current/Best: 5.90/ 7.84 GFLOPS | Progress: (12/20) | 34.36 s
+[Task 25/25] Current/Best: 5.74/ 9.23 GFLOPS | Progress: (16/20) | 36.22 s
+[Task 25/25] Current/Best: 2.93/ 9.23 GFLOPS | Progress: (20/20) | 46.89 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -919,7 +918,8 @@ model using optimized operators to speed up our computations.</p>
<a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="tvm.contrib.graph_executor.GraphModule" class="sphx-glr-backref-module-tvm-contrib-graph_executor sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">module</span></a> <span class="o">=</span> <a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="tvm.contrib.graph_executor.GraphModule" class="sphx-glr-backref-module-tvm-co [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Done.
+/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
</pre></div>
</div>
@@ -975,8 +975,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 414.2256910499964, 'median': 413.89040999999906, 'std': 1.3894004535875637}
-unoptimized: {'mean': 497.23278908998964, 'median': 497.44790824997835, 'std': 0.4699869257931475}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 407.31941859999097, 'median': 407.4516011000014, 'std': 0.8843930754312245}
+unoptimized: {'mean': 495.31586558001436, 'median': 495.21892269999626, 'std': 0.4674847601802359}
</pre></div>
</div>
</div>
@@ -990,7 +990,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 32.072 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 28.408 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 40964fe10..596f4fabd 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -521,7 +521,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.18e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.211e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 42b8ccd6d..512ecd196 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -478,7 +478,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xc804570)), stage(b, placeholder(b, 0xdaee7b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[it [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x2168ee90)), stage(b, placeholder(b, 0x1fe85880)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index da52b0aa0..51067eebe 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:18.347</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:16.875</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,35 +331,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:32.072</p></td>
+<td><p>10:28.408</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.352</p></td>
+<td><p>00:58.239</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:49.882</p></td>
+<td><p>00:55.077</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:30.348</p></td>
+<td><p>00:30.237</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:24.306</p></td>
+<td><p>00:23.559</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.703</p></td>
+<td><p>00:00.695</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.514</p></td>
+<td><p>00:00.502</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.163</p></td>
+<td><p>00:00.152</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
@@ -370,11 +370,11 @@
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
... 149 lines suppressed ...